From couryhouse@aol.com Tue Apr 1 17:55:29 2025 From: ED SHARPE To: cctalk@classiccmp.org Subject: [cctalk] Re: DEC Unibus variants Date: Tue, 01 Apr 2025 17:55:15 +0000 Message-ID: <1356793465.240181.1743530115089@mail.yahoo.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0129053241166956064==" --===============0129053241166956064== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Couryhouse(a)aol.com wishes to unsubscribe Sent from AOL on Android=20 =20 On Sun, Mar 30, 2025 at 3:16 AM, shadoooo via cctalk wrote: The why not use a UniBone comment has merit, what will your (FPGA) > implementation add ? > Well, I know the Unibone! Surely is a very capable system for emulation of older hardware and interfaces. Also performances are good as far as I understand (I don't have one). I have the idea of extending the concept of Unibone. The new design shall be modular, composed by: - a main board hosting the SoM and common interfaces (Ethernet, SD, USB, console) - a bus module for specific bus / machine: support could be added for DEC / Data General / other? - an interchangeable interface module for an hardware device (SMD, Pertec, floppy, RX1/2, RL01/02, other). Any kind of interface could be supported, also for example ADC, DAC, maybe video to some limits...) If you have main module and bus module, you have a similar solution to Unibone / Qbone. However if you need to change bus type, you need to swap only the bus adapter (cheaper). If you have main and interfaces modules, you can control physical devices directly, and do anything with it. For example, you can dump / restore the content of a SMD disk at bit level, no need to know the controller format, etc. Similar to Kyroflux for floppy, but MUCH faster! Alternatively, you could also emulate the device at low level (for example a generic SMD disk). If you have a set of main, bus and interface modules, you can do anything as above, plus you can emulate a controller for a specific machine for a specific device. That said, implementing "anything" would be an infinite effort, but the platform is flexible, so support could be added step-by-step. So why an FPGA? A programmable logic can implement a true digital circuit, where the PRUs in the BeagleBone are processors. This means that in an FPGA the time is always precisely determined by a clock, in PRUs it is affected by the software execution. This means that a PRU can work quite well on an asynchronous bus, provided that sample rate is sufficient, even if not constant. But for a fast synchronous interface, i.e. when time is determined by an external clock, often embedded with data, no software approach can work steadily in my opinion. One thing is true: programming an FPGA is designing a netlist, not developing a software. It can be very hard to debug sometimes, because the approach is more similar to repairing an old board with a Logic Analyzer than perform debugging in software: it's a circuit in a chip, there no step-by-step execution! Nevertheless: I'm a quite good electronic engineer, highly experienced with digital logic and FPGA, so the hardware design wouldn't be a problem. Just a matter of time. Nowadays a SoM with a smaller AMD Zynq7010/7020 (a system-on-chip including an FPGA, plus dual core CPU, lot of peripherals) doesn't cost a lot, and have a great usage flexibility. Also brute computing power is superior to older BB. Why not try? I'm open to your comments. As for the UNIBUS unobtainable transceivers: I think the best solution is to use AM26S10 for drivers, and an LVC logic powered at 3.3v for receivers. Both are active parts costing nuts. I would try this approach. Andrea =20 --===============0129053241166956064==-- From bfranchuk@jetnet.ab.ca Tue Apr 1 21:09:54 2025 From: ben To: cctalk@classiccmp.org Subject: [cctalk] Re: DEC Unibus variants Date: Tue, 01 Apr 2025 15:09:40 -0600 Message-ID: <6f2fe69f-f1ae-4ec7-8558-168b423c165e@jetnet.ab.ca> In-Reply-To: <1356793465.240181.1743530115089@mail.yahoo.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2302339389561243709==" --===============2302339389561243709== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 2025-04-01 11:55 a.m., ED SHARPE via cctalk wrote: > Why not try? > I'm open to your comments. > > As for the UNIBUS unobtainable transceivers: I think the best solution is > to use AM26S10 for drivers, and an LVC logic powered at 3.3v for receivers. > Both are active parts costing nuts. > I would try this approach. > Can a similar bus to the unibus be designed with standard parts using fewer cards?Memory and IO could all fit on one card. > Andrea Ben. --===============2302339389561243709==-- From cz@alembic.crystel.com Tue Apr 1 23:57:56 2025 From: Christopher Zach To: cctalk@classiccmp.org Subject: [cctalk] Re: DEC Unibus variants Date: Tue, 01 Apr 2025 13:57:46 -1000 Message-ID: <473EF3BD-A504-4096-B08D-42C63F5407FE@alembic.crystel.com> In-Reply-To: <6f2fe69f-f1ae-4ec7-8558-168b423c165e@jetnet.ab.ca> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0020119368021662609==" --===============0020119368021662609== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Dec kind of did this with the pdt11 series of systems. The q bus was basicall= y emulated with a pair of 8085 CPUs to emulate Dec peripherals.=20 Fine enough but kind of meh.=20 On April 1, 2025 11:09:40 AM HST, ben via cctalk wr= ote: >On 2025-04-01 11:55 a.m., ED SHARPE via cctalk wrote: >> Why not try? >> I'm open to your comments. >> >> As for the UNIBUS unobtainable transceivers: I think the best solution is >> to use AM26S10 for drivers, and an LVC logic powered at 3.3v for receivers. >> Both are active parts costing nuts. >> I would try this approach. >> >Can a similar bus to the unibus be designed with standard parts using fewer = cards?Memory and IO could all fit on one card. > >> Andrea > Ben. > > --===============0020119368021662609==-- From bill.gunshannon@hotmail.com Wed Apr 2 01:06:22 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Why I am not worried about AI taking over the world! Date: Tue, 01 Apr 2025 21:05:56 -0400 Message-ID: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4149605139697149445==" --===============4149605139697149445== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit So, I am working on another fun project on my trusty old TRS-80's. I need the ability to do multi-line functions which TRS-80 BASIC does not support. But in hopes of finding something where someone added that capability in the distant past (there were lots of features added by various people over time) I decided to just try a Google Search. As we all know Google now begins results with an AI generated answer to your question. This is what I got: -------------------------------------------------------------------------- In TRS-80 BASIC, you can create multi-line functions (subroutines) using the DEF FN statement, allowing you to define a function that can perform a specific task and be called from different parts of your program. Here's how it works: DEF FN Statement: You use the DEF FN statement to define a function, followed by the function name (e.g., FNMyFunction), a set of parentheses for any arguments, and then the code that the function will execute. Example: 10 DEF FNC(X,Y) = X*X + Y*Y defines a function named FNC that takes two arguments (X and Y) and returns the sum of their squares. Function Call: To use the function, you simply call it by its name, passing in the necessary arguments. Example: 20 PRINT FNC(3,4) would print the value returned by the FNC function when called with arguments 3 and 4, which is 25. Multi-line Functions: You can extend the DEF FN statement to span multiple lines, allowing for more complex logic within the function. Example: Code 10 DEF FNC(X,Y) 20 LET TEMP = X * X 30 LET TEMP = TEMP + Y * Y 40 DEF FN END 50 PRINT FNC(3,4) This example defines a function that calculates the sum of squares of two numbers, but the calculation is broken down into multiple lines for readability. Key Points: Line Numbers: TRS-80 BASIC relies on line numbers, so make sure to use them appropriately when defining multi-line functions. Function Name: Function names must start with FN followed by a valid identifier (e.g., FNC, FNMyFunction). DEF FN END: You need to use DEF FN END to mark the end of the function definition, especially when using multi-line functions. Scope: Functions are defined within the scope of the program and are accessible from anywhere in the program. ----------------------------------------------------------------------- Which is both wrong and totally absurd. And I see things all the time about letting AI write your code for you. Does anyone actually trust AI to write code? bill --===============4149605139697149445==-- From bill.gunshannon@hotmail.com Wed Apr 2 01:17:46 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Tue, 01 Apr 2025 21:17:08 -0400 Message-ID: In-Reply-To: =?utf-8?q?=3CLV8P221MB14691D488FF97710998D9511EDAF2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4384457548220275220==" --===============4384457548220275220== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit And now I have to clean the coffee out of my keyboard.... I asked the question with slightly different wording and got a totally different explanation with even more absurd examples. I think I'll ask it to write me a PL/M Compiler in TRS-80 BASIC. :-) bill --===============4384457548220275220==-- From dstalkowski@ody.ca Wed Apr 2 01:31:54 2025 From: dstalkowski@ody.ca To: cctalk@classiccmp.org Subject: [cctalk] DCK11 doc Date: Tue, 01 Apr 2025 21:22:13 -0400 Message-ID: <20250402012213.E68E1BEFCB5@cel2.x> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0623979531094719119==" --===============0623979531094719119== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit I have a scan of the following: LSI-11 BUS INTERFAE CHIPKIT/PROGRAM CONTROL DCK11-AA,-AC October, 1977 Phil Champaigne Logic Products MR2-2/X6645 If someone is interested in a copy, preferably someone who can host it, please contact me. don --===============0623979531094719119==-- From cisin@xenosoft.com Wed Apr 2 01:32:58 2025 From: Fred Cisin To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Tue, 01 Apr 2025 18:32:53 -0700 Message-ID: In-Reply-To: =?utf-8?q?=3CLV8P221MB1469D89D35DFE37C624AED6CEDAF2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3271643112068291181==" --===============3271643112068291181== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit One shortcoming, that has come up before, is that it is taught to NOT say, "I don't know" Somebody asked ChatGPT for the last eight digits of PI, and it gave a sequence of 8 digits. But, somebody else asked, "Is there a last digit of PI?", and it gave a reasonably correct answer. Perhaps, ask it to do it in Level I BASIC, and fit in 4K, . . . -- Grumpy Ol' Fred cisin(a)xenosoft.com On Tue, 1 Apr 2025, Bill Gunshannon via cctalk wrote: > > > And now I have to clean the coffee out of my keyboard.... > > I asked the question with slightly different wording > and got a totally different explanation with even > more absurd examples. I think I'll ask it to write > me a PL/M Compiler in TRS-80 BASIC. :-) > > bill > --===============3271643112068291181==-- From billdegnan@gmail.com Wed Apr 2 02:27:08 2025 From: Bill Degnan To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Tue, 01 Apr 2025 22:26:50 -0400 Message-ID: In-Reply-To: =?utf-8?q?=3CLV8P221MB14691D488FF97710998D9511EDAF2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1321751355870478938==" --===============1321751355870478938== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit I have a book about writing AI code on a Tandy computer from 1981 On Tue, Apr 1, 2025 at 10:01 PM Bill Gunshannon via cctalk < cctalk(a)classiccmp.org> wrote: > > So, I am working on another fun project on my trusty old TRS-80's. > I need the ability to do multi-line functions which TRS-80 BASIC > does not support. But in hopes of finding something where someone > added that capability in the distant past (there were lots of features > added by various people over time) I decided to just try a Google > Search. As we all know Google now begins results with an AI generated > answer to your question. This is what I got: > -------------------------------------------------------------------------- > In TRS-80 BASIC, you can create multi-line functions (subroutines) > using the DEF FN statement, allowing you to define a function that > can perform a specific task and be called from different parts of > your program. > > Here's how it works: > > DEF FN Statement: > > You use the DEF FN statement to define a function, followed by the > function name (e.g., FNMyFunction), a set of parentheses for any > arguments, and then the code that the function will execute. > > Example: 10 DEF FNC(X,Y) = X*X + Y*Y defines a function named FNC > that takes two arguments (X and Y) and returns the sum of their squares. > Function Call: > To use the function, you simply call it by its name, passing in the > necessary arguments. > Example: 20 PRINT FNC(3,4) would print the value returned by the FNC > function when called with arguments 3 and 4, which is 25. > Multi-line Functions: > You can extend the DEF FN statement to span multiple lines, allowing > for more complex logic within the function. > Example: > Code > > 10 DEF FNC(X,Y) > 20 LET TEMP = X * X > 30 LET TEMP = TEMP + Y * Y > 40 DEF FN END > 50 PRINT FNC(3,4) > This example defines a function that calculates the sum of squares > of two numbers, but the calculation is broken down into multiple > lines for readability. > Key Points: > Line Numbers: > TRS-80 BASIC relies on line numbers, so make sure to use them > appropriately when defining multi-line functions. > Function Name: > Function names must start with FN followed by a valid identifier > (e.g., FNC, FNMyFunction). > DEF FN END: > You need to use DEF FN END to mark the end of the function > definition, especially when using multi-line functions. > Scope: > Functions are defined within the scope of the program and are > accessible from anywhere in the program. > ----------------------------------------------------------------------- > > Which is both wrong and totally absurd. > > And I see things all the time about letting AI write your code for you. > Does anyone actually trust AI to write code? > > bill > --===============1321751355870478938==-- From spectre@floodgap.com Wed Apr 2 03:21:16 2025 From: Cameron Kaiser To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Tue, 01 Apr 2025 20:13:28 -0700 Message-ID: <39ba47d2-223e-4902-9005-56dde297c607@floodgap.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0338388803440790259==" --===============0338388803440790259== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable > I have a book about writing AI code on a Tandy computer from 1981 Commodore did one of these too. Very primitive, but I liked it at the time. --=20 ------------------------------------ personal: http://www.cameronkaiser.com/ = -- Cameron Kaiser * Floodgap Systems * www.floodgap.com * ckaiser(a)floodgap.c= om -- Complexity kills. -- Ray Ozzie -------------------------------------------= -- --===============0338388803440790259==-- From cclist@sydex.com Wed Apr 2 04:00:57 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 03:22:39 +0000 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7331213632475166398==" --===============7331213632475166398== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On 4/1/25 18:32, Fred Cisin via cctalk wrote: > One shortcoming, that has come up before, is that it is taught to NOT > say, "I don't know" Apparently, some think that within 10 years, AI will replace doctors and teachers: https://people.com/bill-gates-ai-will-replace-doctors-teachers-in-next-10-yea= rs-11705615 Undoubtedly, it will all be powered by nuclear fusion. I dunno, I'd be a bit leery if my medical treatment would be dictated by an AI, particularly by one that didn't ever say "I don't know..." And back in the dark ages, I studied MEDLARS when it ran on 7090s and tape drives. --Chuck --===============7331213632475166398==-- From bobh@tds.net Wed Apr 2 05:29:02 2025 From: bobh@tds.net To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Tue, 01 Apr 2025 23:59:20 -0400 Message-ID: <2055573423.16473037.1743566360903.JavaMail.zimbra@tds.net> In-Reply-To: =?utf-8?q?=3CLV8P221MB14691D488FF97710998D9511EDAF2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2342080598442752885==" --===============2342080598442752885== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable I did some programming on the TRS-80 Model 4 back in the 80's so it has been = a long time. I did add some functionality using machine code. I had a screen that displaye= d options to the user but took a long time to print it. So the first time it = printed it dump the screen to memory. The every other time it was needed it m= ove the info from the data to the screen. For a function, I used a subroutine. For example: 100 X=3D20 'argument of function 110 GOSUB 1000 'calculate y=3Dmyfunction(x) 120 R=3DA+B*Y 130 continue program 1000 REM this is the myfunction, input x, returns y 1010 function statements 1020 1030 1040 1050 1080 Y=3D .... REM Result of function 1090 RETURN Don't know if that if what you were looking for. Obviously not as clean as R= =3DA*MYFUNCTION(X) ----- Original Message ----- From: "Bill Gunshannon via cctalk" To: cctalk(a)classiccmp.org Cc: "Bill Gunshannon" Sent: Tuesday, April 1, 2025 9:05:56 PM Subject: [cctalk] Why I am not worried about AI taking over the world! So, I am working on another fun project on my trusty old TRS-80's. I need the ability to do multi-line functions which TRS-80 BASIC does not support. But in hopes of finding something where someone added that capability in the distant past (there were lots of features added by various people over time) I decided to just try a Google Search. As we all know Google now begins results with an AI generated answer to your question. This is what I got: -------------------------------------------------------------------------- In TRS-80 BASIC, you can create multi-line functions (subroutines) using the DEF FN statement, allowing you to define a function that can perform a specific task and be called from different parts of your program. Here's how it works: DEF FN Statement: You use the DEF FN statement to define a function, followed by the function name (e.g., FNMyFunction), a set of parentheses for any arguments, and then the code that the function will execute. Example: 10 DEF FNC(X,Y) =3D X*X + Y*Y defines a function named FNC that takes two arguments (X and Y) and returns the sum of their squares. Function Call: To use the function, you simply call it by its name, passing in the necessary arguments. Example: 20 PRINT FNC(3,4) would print the value returned by the FNC function when called with arguments 3 and 4, which is 25. Multi-line Functions: You can extend the DEF FN statement to span multiple lines, allowing for more complex logic within the function. Example: Code 10 DEF FNC(X,Y) 20 LET TEMP =3D X * X 30 LET TEMP =3D TEMP + Y * Y 40 DEF FN END 50 PRINT FNC(3,4) This example defines a function that calculates the sum of squares of two numbers, but the calculation is broken down into multiple lines for readability. Key Points: Line Numbers: TRS-80 BASIC relies on line numbers, so make sure to use them appropriately when defining multi-line functions. Function Name: Function names must start with FN followed by a valid identifier (e.g., FNC, FNMyFunction). DEF FN END: You need to use DEF FN END to mark the end of the function definition, especially when using multi-line functions. Scope: Functions are defined within the scope of the program and are accessible from anywhere in the program. ----------------------------------------------------------------------- Which is both wrong and totally absurd. And I see things all the time about letting AI write your code for you. Does anyone actually trust AI to write code? bill --===============2342080598442752885==-- From artgodwin@gmail.com Wed Apr 2 11:19:29 2025 From: Adrian Godwin To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 12:19:13 +0100 Message-ID: In-Reply-To: <39ba47d2-223e-4902-9005-56dde297c607@floodgap.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============9039927088469679573==" --===============9039927088469679573== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit I'm not worried about AI taking over the world. What worries me is politicians and commercial management believing the hype and turning the world over to AI before it works properly. On Wed, Apr 2, 2025 at 8:36 AM Cameron Kaiser via cctalk < cctalk(a)classiccmp.org> wrote: > > > I have a book about writing AI code on a Tandy computer from 1981 > > Commodore did one of these too. Very primitive, but I liked it at the time. > > -- > ------------------------------------ personal: > http://www.cameronkaiser.com/ -- > Cameron Kaiser * Floodgap Systems * www.floodgap.com * > ckaiser(a)floodgap.com > -- Complexity kills. -- Ray Ozzie > --------------------------------------------- > > --===============9039927088469679573==-- From lists@glitchwrks.com Wed Apr 2 14:15:57 2025 From: Jonathan Chapman To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 14:06:54 +0000 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6783201056352934130==" --===============6783201056352934130== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On Tuesday, April 1st, 2025 at 21:32, Fred Cisin via cctalk wrote: > One shortcoming, that has come up before, is that it is taught to NOT say, > "I don't know" Heh, I worked with a guy like that once. Unfortunately, he was in sales, so f= ield engineering then got to explain that what he'd sold them was actually no= t feasible.=20 Thanks, Jonathan --===============6783201056352934130==-- From billdegnan@gmail.com Wed Apr 2 14:38:12 2025 From: Bill Degnan To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 10:37:43 -0400 Message-ID: In-Reply-To: <39ba47d2-223e-4902-9005-56dde297c607@floodgap.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1443721800007755082==" --===============1443721800007755082== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit I did a talk at this year's Trenton Computer Festival on the history of AI. On Wed, Apr 2, 2025 at 3:36 AM Cameron Kaiser via cctalk < cctalk(a)classiccmp.org> wrote: > > > I have a book about writing AI code on a Tandy computer from 1981 > > Commodore did one of these too. Very primitive, but I liked it at the time. > > -- > ------------------------------------ personal: > http://www.cameronkaiser.com/ -- > Cameron Kaiser * Floodgap Systems * www.floodgap.com * > ckaiser(a)floodgap.com > -- Complexity kills. -- Ray Ozzie > --------------------------------------------- > > --===============1443721800007755082==-- From bill.gunshannon@hotmail.com Wed Apr 2 16:35:43 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 12:35:14 -0400 Message-ID: In-Reply-To: =?utf-8?q?=3CwcsUKAn2WvbLgEMsdlmR=5FsPK-0intgwmdtGNjqJ=5FicUgHJ?= =?utf-8?q?eKwcvqA3E1NpbG093ljcDyBnyV2UdqIp4WQ=5FmxV8x6q6jI3MtgPiZ8LQBiuu0?= =?utf-8?q?=3D=40glitchwrks=2Ecom=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7798901634215413549==" --===============7798901634215413549== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On 4/2/2025 10:06 AM, Jonathan Chapman via cctalk wrote: > On Tuesday, April 1st, 2025 at 21:32, Fred Cisin via cctalk wrote: >=20 >> One shortcoming, that has come up before, is that it is taught to NOT say, >> "I don't know" >=20 > Heh, I worked with a guy like that once. Unfortunately, he was in sales, so= field engineering then got to explain that what he'd sold them was actually = not feasible. >=20 In my days as a beltway bandit I was very popular as a pre-sales system engineer. At least, with the customers. I never let a salesman try to sell something I knew engineering could never deliver. bill --===============7798901634215413549==-- From ard.p850ug1@gmail.com Wed Apr 2 16:46:42 2025 From: Tony Duell To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 17:46:23 +0100 Message-ID: In-Reply-To: =?utf-8?q?=3CLV8P221MB14691D488FF97710998D9511EDAF2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5340976926612142640==" --===============5340976926612142640== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On Wed, Apr 2, 2025 at 3:01 AM Bill Gunshannon via cctalk wrote: > > > So, I am working on another fun project on my trusty old TRS-80's. > I need the ability to do multi-line functions which TRS-80 BASIC > does not support. Actually there was an offical BASIC (meaning sold by Tandy/Radio Shack) for one family of TRS-80 machines that did support multi-line (named) procedures. Not strictly functons as there was no return value but as you can pass parameters by reference you can return values that way. And line numbers were optional. It's Microware's BASIC-09 under OS-9 on the CoCo of course. Quite the finest 8-bit BASIC that I have ever used. -tony --===============5340976926612142640==-- From bill.gunshannon@hotmail.com Wed Apr 2 16:47:22 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 12:46:44 -0400 Message-ID: In-Reply-To: <2055573423.16473037.1743566360903.JavaMail.zimbra@tds.net> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6615410050631407994==" --===============6615410050631407994== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On 4/1/2025 11:59 PM, bobh(a)tds.net wrote: > I did some programming on the TRS-80 Model 4 back in the 80's so it has bee= n a long time. >=20 > I did add some functionality using machine code. I had a screen that displa= yed options to the user but took a long time to print it. So the first time i= t printed it dump the screen to memory. The every other time it was needed it= move the info from the data to the screen. >=20 > For a function, I used a subroutine. For example: > 100 X=3D20 'argument of function > 110 GOSUB 1000 'calculate y=3Dmyfunction(x) > 120 R=3DA+B*Y > 130 continue program >=20 >=20 > 1000 REM this is the myfunction, input x, returns y > 1010 function statements > 1020 > 1030 > 1040 > 1050 >=20 > 1080 Y=3D .... REM Result of function > 1090 RETURN >=20 > Don't know if that if what you were looking for. Obviously not as clean as = R=3DA*MYFUNCTION(X) >=20 >=20 I knew (and tried a little bit to see how hard it would be) that method.=20 But the catch is at this stage I am trying to convert a program from NorthStar BASIC to TRS-80 BASIC. And all the multi-line functions are already there but, obviously, need to be replaced. Along with a lot of other conversions. Like the fact that there really are no strings in NorthStar BASIC. They are actually character arrays and bring with that some quirks that TRS-80 BASIC doesn't have. Because this is just a starting point for my long term project (really long term - I started this back when the TRS-80 was still mainline :-) I am thinking I will give up efficiency and just put the function code inline everywhere there is a call to that function. bill --===============6615410050631407994==-- From bill.gunshannon@hotmail.com Wed Apr 2 16:54:55 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 12:54:25 -0400 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8337365016175289182==" --===============8337365016175289182== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On 4/2/2025 12:46 PM, Tony Duell wrote: > On Wed, Apr 2, 2025 at 3:01 AM Bill Gunshannon via cctalk > wrote: >> >> >> So, I am working on another fun project on my trusty old TRS-80's. >> I need the ability to do multi-line functions which TRS-80 BASIC >> does not support. > > Actually there was an offical BASIC (meaning sold by Tandy/Radio > Shack) for one family of TRS-80 machines that did support multi-line > (named) procedures. > > Not strictly functons as there was no return value but as you can pass > parameters by reference you can return values that way. > > And line numbers were optional. > > It's Microware's BASIC-09 under OS-9 on the CoCo of course. Quite the > finest 8-bit BASIC that I have ever used. > Not meaning to be pedantic, but, OS-9 ran on the COCO which was never called a TRS-80 that I know of. The COCO had the usual version of Microsoft BASIC found on the TRS-80's and while Radio Shack sold Basic09 it was not their product, it was from Microware just like OS-9. I have used it and this project may eventually drift in that direction after the TRS-80 part is done, as portability is one of my goals. I have at least one and maybe more, I forget, Basic09 programs on Rosetta Code. bill --===============8337365016175289182==-- From ard.p850ug1@gmail.com Wed Apr 2 17:07:32 2025 From: Tony Duell To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 18:07:16 +0100 Message-ID: In-Reply-To: =?utf-8?q?=3CLV8P221MB1469DB61152686FE27002106EDAF2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5228256680693048259==" --===============5228256680693048259== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On Wed, Apr 2, 2025 at 5:54 PM Bill Gunshannon via cctalk wrote: > Not meaning to be pedantic, but, OS-9 ran on the COCO which > was never called a TRS-80 that I know of. The COCO had the The service manual for the CoCo 2 is titled : 'Radio Shack Service Manual TRS-80 (R) Color Computer 2' The CoCo 3 manual does not say TRS-80 on it through -tony --===============5228256680693048259==-- From jfoust@threedee.com Wed Apr 2 18:12:01 2025 From: John Foust To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 12:44:59 -0500 Message-ID: <20250402181157.5778E86C9C@classiccmp.org> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1152202869125566601==" --===============1152202869125566601== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit "Ancient BASIC dialects" seems like a rather small obscure domain and as they say, they're not making any more of them. I'd think that if you trained an AI on enough examples, they'd do much better. The BASIC language isn't that complex compared to modern languages where people are finding AI as a useful assistant, like it or not. Think of it like old-school "pair programming" that gives you a friend in your cube to talk to. - John --===============1152202869125566601==-- From cclist@sydex.com Wed Apr 2 18:34:41 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 18:34:31 +0000 Message-ID: <3dd1de81-8cc1-43d3-8bd9-239cd10dbe54@sydex.com> In-Reply-To: <20250402181157.5778E86C9C@classiccmp.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3484675089146226552==" --===============3484675089146226552== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/2/25 10:44, John Foust via cctalk wrote: > > "Ancient BASIC dialects" seems like a rather small obscure domain > and as they say, they're not making any more of them. I'd think > that if you trained an AI on enough examples, they'd do much better. > The BASIC language isn't that complex compared to modern languages > where people are finding AI as a useful assistant, like it or not. > Think of it like old-school "pair programming" that gives you > a friend in your cube to talk to. BASIC is not "ancient" although I suppose one could assign a vintage year. Plugboard programming is ancient, at least in the area of electronic computing. --Chuck --===============3484675089146226552==-- From julf@julf.com Wed Apr 2 18:45:12 2025 From: Johan Helsingius To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 20:37:13 +0200 Message-ID: <5a9c9223-ec2c-4a32-b9d5-2439f404f99a@Julf.com> In-Reply-To: <20250402181157.5778E86C9C@classiccmp.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1389748468355808646==" --===============1389748468355808646== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 02/04/2025 19:44, John Foust via cctalk wrote: > Think of it like old-school "pair programming" that gives you > a friend in your cube to talk to. As long as you remember that the "AI" (really not AI, just a generative large language model) doesn't actually understand what it is doing - it is just telling you what people usually wrote in that situation. Julf --===============1389748468355808646==-- From bill.gunshannon@hotmail.com Thu Apr 3 00:11:17 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 20:10:23 -0400 Message-ID: In-Reply-To: <5a9c9223-ec2c-4a32-b9d5-2439f404f99a@Julf.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6438333154938405094==" --===============6438333154938405094== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/2/2025 2:37 PM, Johan Helsingius via cctalk wrote: > On 02/04/2025 19:44, John Foust via cctalk wrote: >> Think of it like old-school "pair programming" that gives you >> a friend in your cube to talk to. > > As long as you remember that the "AI" (really not AI, just a > generative large language model) doesn't actually understand > what it is doing - it is just telling you what people usually > wrote in that situation. > Except that no one ever wrote code like it offered me cause it was just plain wrong and wouldn't work. bill --===============6438333154938405094==-- From bfranchuk@jetnet.ab.ca Thu Apr 3 01:31:38 2025 From: ben To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 19:31:32 -0600 Message-ID: <4e31b7f3-3303-466c-8100-a71093af9ae8@jetnet.ab.ca> In-Reply-To: =?utf-8?q?=3CLV8P221MB14690BBBE5C86442714EF2EDEDAE2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5559342239368807035==" --===============5559342239368807035== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 2025-04-02 6:10 p.m., Bill Gunshannon via cctalk wrote: > > Except that no one ever wrote code like it offered me cause > it was just plain wrong and wouldn't work. I write code like that all the time:) > bill > Have the tools really improved all that much to write better code or debug it since the early 80's? --===============5559342239368807035==-- From bill.gunshannon@hotmail.com Thu Apr 3 02:15:29 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Wed, 02 Apr 2025 22:14:58 -0400 Message-ID: In-Reply-To: <4e31b7f3-3303-466c-8100-a71093af9ae8@jetnet.ab.ca> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1516584249366893152==" --===============1516584249366893152== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/2/2025 9:31 PM, ben via cctalk wrote: > On 2025-04-02 6:10 p.m., Bill Gunshannon via cctalk wrote: >> >> Except that no one ever wrote code like it offered me cause >> it was just plain wrong and wouldn't work. > > I write code like that all the time:) > What would you write code like that for? It won't run. It is claiming the existence of and is using things that don't exist on the system it was providing code for? bill --===============1516584249366893152==-- From julf@julf.com Thu Apr 3 06:17:18 2025 From: Johan Helsingius To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 08:16:14 +0200 Message-ID: <8be92120-9c1f-47fa-b864-9085d0b0099e@Julf.com> In-Reply-To: =?utf-8?q?=3CLV8P221MB14690BBBE5C86442714EF2EDEDAE2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8342539964401465694==" --===============8342539964401465694== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 03/04/2025 02:10, Bill Gunshannon via cctalk wrote: > Except that no one ever wrote code like it offered me cause > it was just plain wrong and wouldn't work. Indeed. As I wrote it has no actual understanding. It just combines things based on statistics. It is like Mark V. Shaney, the chatbot that Rob Pike and Bruce Ellis did in the 1980s, but with enormous amounts of computing power (and source material from the net) thrown at it. https://en.wikipedia.org/wiki/Mark_V._Shaney Julf --===============8342539964401465694==-- From bfranchuk@jetnet.ab.ca Thu Apr 3 06:44:57 2025 From: ben To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 00:44:47 -0600 Message-ID: In-Reply-To: <8be92120-9c1f-47fa-b864-9085d0b0099e@Julf.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2249656906235010453==" --===============2249656906235010453== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 2025-04-03 12:16 a.m., Johan Helsingius via cctalk wrote: > Indeed. As I wrote it has no actual understanding. It just combines > things based on statistics. > > It is like Mark V. Shaney, the chatbot that Rob Pike and > Bruce Ellis did in the 1980s, but with enormous amounts > of computing power (and source material from the net) > thrown at it. > Other than in Si-Fi novels and movies, what use is a AI? Ben. --===============2249656906235010453==-- From artgodwin@gmail.com Thu Apr 3 07:57:47 2025 From: Adrian Godwin To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 08:41:46 +0100 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7949972381856891663==" --===============7949972381856891663== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable AIs that are wise rather than idiot-savants ought to be useful, in the way sci-fi writers imagine. However, statistical systems can't surpass their training, and their training contains flaws - many, in the case of uncurated internet grabs. And the compulsion to not admit to a lack of knowledge and substiture - perhaps unknowingly - hallucinations is absurd. I cannot see any justification for that. On Thu, Apr 3, 2025 at 8:01=E2=80=AFAM ben via cctalk wrote: > On 2025-04-03 12:16 a.m., Johan Helsingius via cctalk wrote: > > > Indeed. As I wrote it has no actual understanding. It just combines > > things based on statistics. > > > > It is like Mark V. Shaney, the chatbot that Rob Pike and > > Bruce Ellis did in the 1980s, but with enormous amounts > > of computing power (and source material from the net) > > thrown at it. > > > Other than in Si-Fi novels and movies, what use is a AI? > Ben. > --===============7949972381856891663==-- From doc@vaxen.net Thu Apr 3 10:11:54 2025 From: Doc Shipley To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 05:02:33 -0500 Message-ID: <0f44243c-11b7-4978-8aa0-57963397ff39@vaxen.net> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6610152550476361208==" --===============6610152550476361208== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/3/25 02:41, Adrian Godwin via cctalk wrote: > AIs that are wise rather than idiot-savants ought to be useful, in the way > sci-fi writers imagine. > However, statistical systems can't surpass their training, and their > training contains flaws - many, in the case of uncurated internet grabs. > And the compulsion to not admit to a lack of knowledge and substiture - > perhaps unknowingly - hallucinations is absurd. I cannot see any > justification for that. The justification for that compulsion is fairly obvious if you take "do no harm" out of the equation. An AI that says "I don't know" loses more business, aka profit, than an AI that spouts garbage. AI and LLMs strengthen my belief that humanity's technology surpassed our ethics decades ago. Like, trampled any useful code of behavior into the dirt. I don't have the faintest idea what to do about that, either. Doc --===============6610152550476361208==-- From artgodwin@gmail.com Thu Apr 3 10:58:42 2025 From: Adrian Godwin To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 11:58:22 +0100 Message-ID: In-Reply-To: <0f44243c-11b7-4978-8aa0-57963397ff39@vaxen.net> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============9215085119149159827==" --===============9215085119149159827== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit Yes. I should have said 'any honest justification' But if we can expect only dishonesty from their promoters, there's no future for them. On Thu, Apr 3, 2025 at 11:31 AM Doc Shipley via cctalk < cctalk(a)classiccmp.org> wrote: > On 4/3/25 02:41, Adrian Godwin via cctalk wrote: > > AIs that are wise rather than idiot-savants ought to be useful, in the > way > > sci-fi writers imagine. > > However, statistical systems can't surpass their training, and their > > training contains flaws - many, in the case of uncurated internet grabs. > > And the compulsion to not admit to a lack of knowledge and substiture - > > perhaps unknowingly - hallucinations is absurd. I cannot see any > > justification for that. > > The justification for that compulsion is fairly obvious if you take > "do no harm" out of the equation. An AI that says "I don't know" loses > more business, aka profit, than an AI that spouts garbage. > > AI and LLMs strengthen my belief that humanity's technology surpassed > our ethics decades ago. Like, trampled any useful code of behavior into > the dirt. I don't have the faintest idea what to do about that, either. > > > Doc > --===============9215085119149159827==-- From c.murray.mccullough@gmail.com Thu Apr 3 14:43:43 2025 From: Murray McCullough To: cctalk@classiccmp.org Subject: [cctalk] Altair BASIC Source Code released Date: Thu, 03 Apr 2025 10:43:31 -0400 Message-ID: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4041482880503291316==" --===============4041482880503291316== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit I wonder if this helped start the microcomputer revolution, OS-side, or was this a re-hash of what already was available? It's a historical event as per se but much more than that I'm not sure! Happy computing! Murray 🙂 --===============4041482880503291316==-- From blstuart@bellsouth.net Thu Apr 3 18:08:41 2025 From: "Brian L. Stuart" To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 18:08:52 +0000 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5614078247638742371==" --===============5614078247638742371== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On Thu, Apr 03, 2025 at 12:44:47AM -0600, ben via cctalk wrote: > On 2025-04-03 12:16 a.m., Johan Helsingius via cctalk wrote: > > > Indeed. As I wrote it has no actual understanding. It just combines > > things based on statistics. > > > > It is like Mark V. Shaney, the chatbot that Rob Pike and > > Bruce Ellis did in the 1980s, but with enormous amounts > > of computing power (and source material from the net) > > thrown at it. > > > Other than in Si-Fi novels and movies, what use is a AI? The issue arises in that in the popular conception AI is a thing where a grammatical construction like "an AI" makes sense. However, that's not the way to look at it. AI is a subject of study, like Physics or Electrial Engineering. One doesn't talk about "a physics" or "an electrical engineering." So what is the subject of AI? It's studying the phenomenon of intelligence and the mechanisms of the brain using the computer as a laboratory and in ways that we can't do with ourselves. What then is an LLM in that context? It's an experiment in the subfield of AI called Natural Language Processing. Is it possible for such an experiment to produce a useful tool? Maybe, but so far I haven't seen anything to suggest that this one has. So far, all of the output I've seen triggers a recognition in my brain of a student who doesn't understand the question and is throwing information at the question, hoping something will stick. The fact that a significant part of the world seems to see that behavior as an example of intelligence is the depressing part. BLS --===============5614078247638742371==-- From michael.99.thompson@gmail.com Thu Apr 3 18:40:40 2025 From: Michael Thompson To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 14:40:23 -0400 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1521513580805653798==" --===============1521513580805653798== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit I wonder if the source, not just the listing is available. It would be interesting to build it on TOPS-10 running on a KA-10 simulated on Simh. On Thu, Apr 3, 2025 at 2:21 PM Murray McCullough via cctalk < cctalk(a)classiccmp.org> wrote: > I wonder if this helped start the microcomputer revolution, OS-side, or > was this a re-hash of what already was available? > > It's a historical event as per se but much more than that I'm not sure! > > Happy computing! > > Murray 🙂 > -- Michael Thompson --===============1521513580805653798==-- From ylee@columbia.edu Thu Apr 3 18:51:18 2025 From: Yeechang Lee To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 11:43:15 -0700 Message-ID: <26606.54979.334690.219283@dobie-old.ylee.org> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3673888589813894208==" --===============3673888589813894208== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Tony Duell says: > The CoCo 3 manual does not say TRS-80 on it through By then the computers decided that "TRS-80"/"Radio Shack" was a liability, so= called new computers "Tandy". Thus Tandy 1000, Tandy 6000 (succeeding the TR= S-80 Model 16B and Model 12), and Tandy Color Computer 3. --=20 geo:37.783333,-122.416667 --===============3673888589813894208==-- From cclist@sydex.com Thu Apr 3 19:13:27 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 19:13:13 +0000 Message-ID: <06f760d5-3ebd-4993-9bf3-4b1c06ba58b0@sydex.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8470041360884639621==" --===============8470041360884639621== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/3/25 11:40, Michael Thompson via cctalk wrote: > I wonder if the source, not just the listing is available. It would be > interesting to build it on TOPS-10 running on a KA-10 simulated on Simh. > Given the extent that it was pirated in the early days, I strongly suspect that there have been disassembled sources around for at least a few decades. --Chuck --===============8470041360884639621==-- From milovelimirovic@gmail.com Thu Apr 3 19:26:01 2025 From: Milo =?utf-8?q?Velimirovi=C4=87?= To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 14:25:44 -0500 Message-ID: <311BBE74-F6D1-4312-A4FB-14A600FD4AB8@gmail.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8552870251153389086==" --===============8552870251153389086== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Altair BASIC would probably be easier to get working on an Altair 8800 simula= ted on simh. > On Apr 3, 2025, at 1:40=E2=80=AFPM, Michael Thompson via cctalk wrote: >=20 > I wonder if the source, not just the listing is available. It would be > interesting to build it on TOPS-10 running on a KA-10 simulated on Simh. >=20 > On Thu, Apr 3, 2025 at 2:21=E2=80=AFPM Murray McCullough via cctalk < > cctalk(a)classiccmp.org> wrote: >=20 >> I wonder if this helped start the microcomputer revolution, OS-side, or >> was this a re-hash of what already was available? >>=20 >> It's a historical event as per se but much more than that I'm not sure! >>=20 >> Happy computing! >>=20 >> Murray =F0=9F=99=82 >>=20 >=20 >=20 > --=20 > Michael Thompson --===============8552870251153389086==-- From rgrabau1@verizon.net Thu Apr 3 19:33:18 2025 From: Bob Grabau To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 15:32:58 -0400 Message-ID: <877c3434-c255-48d8-857c-be811a7a873d@verizon.net> In-Reply-To: <06f760d5-3ebd-4993-9bf3-4b1c06ba58b0@sydex.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2319746597944150445==" --===============2319746597944150445== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit As my memory serves, there was a class given by the Southern California Computer Society (SCCS) in which the disassembled the Altair Basic (not sure if it was the 4k or 8k version) and used the output of that disassembly for the class. There was a guy who had the complete annotated (by the class) of the source as printed out copies in his trunk, which he just handed out to anyone that asked for it.   This was somewhere between 1975-1978 (76-77 most likely) when I was a member of SCCS. Bob On 4/3/2025 3:13 PM, Chuck Guzis via cctalk wrote: > On 4/3/25 11:40, Michael Thompson via cctalk wrote: >> I wonder if the source, not just the listing is available. It would be >> interesting to build it on TOPS-10 running on a KA-10 simulated on Simh. >> > Given the extent that it was pirated in the early days, I strongly > suspect that there have been disassembled sources around for at least a > few decades. > > --Chuck -- Bob Grabau http://www.astrohbg.org http://www.cherrysprings.org Our Star Party for 2025: June 19-22, 2025 at Cherry Springs State Park, PA --===============2319746597944150445==-- From van.snyder@sbcglobal.net Thu Apr 3 20:18:49 2025 From: Van Snyder To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 13:17:37 -0700 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============9120541732601108370==" --===============9120541732601108370== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On Thu, 2025-04-03 at 10:43 -0400, Murray McCullough via cctalk wrote: > I wonder if this helped start the microcomputer revolution, OS-side,  > or > was this a re-hash of what already was available? In 1972 on Univac 1108 at JPL, I developed an interactive numerical math package, similar to but much smaller than Matlab, called Engineer's Calculator Language or ECL. ECL was expanded by Phil Roberts and became Quick, which was used for spacecraft trajectory planning. Jack Hatfield used the language-processing and memory-management infrastructure I developed for a project called JPL Management Information System or JPLMIS, based on a "network" (not internet) database organization (relational databases and SQL hadn't yet been invented). Jack Hatfield resigned when his name was omitted from the user guide and management refused to correct it. Jeb Long continued that project and it became Data Information System or JPLDIS Jeb was interested in microcomputers, and had an Altair 8800 in his office. After a meeting of the JPL microcomputer club, he gave the source code to Wayne Ratliff, who hand-compiled about a quarter of the original Fortran code to 8080 assembler and called it Vulcan. He took it to George Tate, who teamed up with Hal Lashlee to form Ashton- Tate (there was never any Ashton). Ashton-Tate couldn't sell it as Vulcan because Harris already had an OS of that name, so they changed it to dBase, and later dBase II. Foxpro was an independent clone of it. Ratliff gets public credit for my work, Jack Hatfield's work, and Jeb Long's work. But at least Jeb got 1/16 of retail for every dBase sold — and retired before age 40. --===============9120541732601108370==-- From merlyn@geeks.org Thu Apr 3 20:27:47 2025 From: Doug McIntyre To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 15:20:35 -0500 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8920263237367863112==" --===============8920263237367863112== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On Thu, Apr 03, 2025 at 02:40:23PM -0400, Michael Thompson via cctalk wrote: > I wonder if the source, not just the listing is available. It would be > interesting to build it on TOPS-10 running on a KA-10 simulated on Simh. While there have been plenty of disassemblies around, I assume this thread is the announcement of Bill Gate's releasing the actual source code up on his blog.. https://www.gatesnotes.com/microsoft-original-source-code Looks like you can get a PDF of scans of a greenbar printout of his/Paul Alle= n's source from 1975.=20 As described in Bill Gate's recent auto-biography (Source Code: My Beginnings), or Paul Allen's auto-biography (Idea Man), they developed their BASIC code on the PDP-10 because they both had been hacking on the PDP-10 for their previous projects for a couple years?, and Paul Allen had written an 8080 emulator (somehow with macro?) for the system, and they could emulate the 8080 chip before the Altair 8800 existed (for real, not the dummy one they pre-announced in the magazine ahead of it actually shipping). So I don't think the 8080 Source code of Altair BASIC would do you much on the PDP-10 without also having Paul Allen's macro package for the 8080 emulation and developer system that they were doing. As they explained in their books, an Altair with 4k wasn't exactly a system anything could be developed on, so the various PDP-10's they rented time on was utilized as the dev system, and they seeked that one out because they had the support system already in place for what they were doing. (ie. emulator/macro package/assembler/linker) They later were able to successfully do the same emulation trick with the oth= er micro CPUs that they wrote basic for until PCs could actually start hosting dev environments (many= years later). --===============8920263237367863112==-- From jfoust@threedee.com Thu Apr 3 21:22:10 2025 From: John Foust To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 16:21:45 -0500 Message-ID: <20250403212206.7E27286196@classiccmp.org> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4376085985795566547==" --===============4376085985795566547== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: >Apparently, some think that within 10 years, AI will replace doctors and >teachers: It's one thing to say that AI methods have been shown to give better diagnoses in some situations than the humans, it's quite another to suggest we won't need doctors. In my neck of the woods, even doctors have been greatly supplanted by physician assistants. I'm as skeptical as they come, and I have plenty of criticisms of AI as implemented today, but I've also been confounded to discover how useful it can be when programming. It's often better than googling and copy-and-pasting from Stackoverflow. I've generally used Copilot as it comes with M365. In a recent Perl tool that needed a few dozen regular expressions, it was very handy, providing not only correct regexs but also snippets of the surrounding code. In another task where I wanted to quickly generate a text-based profile of a computer's specifications and components, it was very helpful in writing a bunch of PowerShell. Did it hallucinate? Perhaps once out of several dozen things I asked it, and in that case, it was easy to see that the two clauses of the if-then were the same. I've heard similar puzzlement from a very experienced programmer friend who told me about the way his IDE would now suggest code to him while he was typing, and he thought the suggested code was good and very similar if not identical to what he was about to write. - John --===============4376085985795566547==-- From cclist@sydex.com Thu Apr 3 21:38:07 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 21:37:59 +0000 Message-ID: <8b13441b-ed6a-476f-906f-5712906874ff@sydex.com> In-Reply-To: <20250403212206.7E27286196@classiccmp.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2225862431749294893==" --===============2225862431749294893== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/3/25 14:21, John Foust via cctalk wrote: > At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: > In another task where I wanted to quickly generate a text-based > profile of a computer's specifications and components, it was very > helpful in writing a bunch of PowerShell. Did it hallucinate? > Perhaps once out of several dozen things I asked it, and in that > case, it was easy to see that the two clauses of the if-then were > the same. Interesting. I got no help at all from ChatGPT when working through some IBM 7090 code. --Chuck --===============2225862431749294893==-- From wrcooke@wrcooke.net Thu Apr 3 21:51:04 2025 From: wrcooke@wrcooke.net To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 17:50:58 -0400 Message-ID: <1611713586.695160.1743717058727@email.ionos.com> In-Reply-To: <8b13441b-ed6a-476f-906f-5712906874ff@sydex.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2501124165802013763==" --===============2501124165802013763== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable > On 04/03/2025 5:37 PM EDT Chuck Guzis via cctalk = wrote: > > > On 4/3/25 14:21, John Foust via cctalk wrote: > > At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: > > > In another task where I wanted to quickly generate a text-based > > profile of a computer's specifications and components, it was very > > helpful in writing a bunch of PowerShell. Did it hallucinate? > > Perhaps once out of several dozen things I asked it, and in that > > case, it was easy to see that the two clauses of the if-then were > > the same. > > Interesting. I got no help at all from ChatGPT when working through > some IBM 7090 code. > > --Chuck My experience has been much like John's. In my company of 10,000 ish employe= es, the entire company is "strongly encouraged" to use various "AI" tools mad= e available. The encouragement comes directly from the CEO (and all his mini= ons echo it) during his monthly video addresses. So, all of us who write code have copilot licenses and they actually track ho= w much we use it (can you say layoff? I knew you could.) What I have found = is that the short suggestions of a half dozen lines or more are often pretty = good. It's the bad ones I have to fight the system to NOT take that eat up t= he time. I usually could have just written those half dozen lines faster. B= ut sometimes it helps a lot. Apparently it tracks names and kind find the co= rrect variable or constant faster than I could. A couple of coworkers have g= iven a good description: good for boilerplate code. As for chatgpt not doing well, I suspect that is largely due to it being a ge= neral purpose "question answerer" rather than a tool specifically for program= ming. I know of at least one person who did, however, get hired based mostly= on code written by chatgpt. But he didn't last long. Will --===============2501124165802013763==-- From steven@malikoff.com Thu Apr 3 21:52:07 2025 From: "steven@malikoff.com steven@malikoff.com" To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Fri, 04 Apr 2025 07:46:57 +1000 Message-ID: <709306628.2966327.1743716817285@webmail-oxcs.register.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0267841166296656435==" --===============0267841166296656435== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Murray said > On 04/04/2025 12:43 AM AEST Murray McCullough via cctalk wrote: > I wonder if this helped start the microcomputer revolution, OS-side, or > was this a re-hash of what already was available? >=20 > It's a historical event as per se but much more than that I'm not sure! Looking through the PDF listing, no matter what you may think of Bill and Mic= rosoft etc. I have to say that is some very well documented code. It's at the= other end of the spectrum from 'the code is the comments' mentality that see= ms to afflict modern programming. Steve --===============0267841166296656435==-- From cc@alderson.users.panix.com Thu Apr 3 22:10:12 2025 From: Rich Alderson To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Thu, 03 Apr 2025 17:50:14 -0400 Message-ID: <4ZTFlV4dv3zfYm@panix5.panix.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2564487248644357352==" --===============2564487248644357352== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable > Date: Thu, 3 Apr 2025 15:20:35 -0500 > From: Doug McIntyre via cctalk > On Thu, Apr 03, 2025 at 02:40:23PM -0400, Michael Thompson via cctalk wrote: >> I wonder if the source, not just the listing is available. It would be >> interesting to build it on TOPS-10 running on a KA-10 simulated on Simh. Perhaps, although at LCM (long before the "+L" was added--or we opened to the public) we built it on the 2065 running Tops-10 v7.04. Architecture is architecture, after all. [ snip ] > As described in Bill Gate's recent auto-biography (Source Code: My > Beginnings), or Paul Allen's auto-biography (Idea Man), they developed their > BASIC code on the PDP-10 because they both had been hacking on the PDP-10 f= or > their previous projects for a couple years?, and Paul Allen had written an > 8080 emulator (somehow with macro?) for the system, and they could emulate > the 8080 chip before the Altair 8800 existed (for real, not the dummy one > they pre-announced in the magazine ahead of it actually shipping). Allen and Gates began programming on the PDP-10 in 1970, when Paul was a juni= or and Bill was a freshman. They were good enough that after Paul graduated, th= ey (along with 3 of their friends) got jobs programming the PDP-10s for the control systems at the Bonneville Power Adminstration for the summer of 1971. As for Paul's 8080 simulator, it was indeed made up of Macro-10 macros (which can be very sophisticated) which processed 8080 assembler into user-mode UUOs and a set of UUO routines which perform the work defined for each such 8080 instruction. The simulator is used by including its source code with the 8080 source code to be executed, assembling everything, and executing the result. It's a marvelous piece of programming which utilizes the PDP-10 architecture to its fullest. > So I don't think the 8080 Source code of Altair BASIC would do you > much on the PDP-10 without also having Paul Allen's macro package for > the 8080 emulation and developer system that they were doing. As they > explained in their books, an Altair with 4k wasn't exactly a system > anything could be developed on, so the various PDP-10's they rented > time on was utilized as the dev system, and they seeked that one out > because they had the support system already in place for what they > were doing. (ie. emulator/macro package/assembler/linker) Rented time on while they were located in Albuquerque, then outright owned on= ce they moved the company to Bellevue. > They later were able to successfully do the same emulation trick with the > other micro CPUs that they wrote basic for until PCs could actually start > hosting dev environments (many years later). A friend of mine, M$ employee no. 11, was one of the developers of the other macro packages for different micro acrchitectures. Rich [1] For the non-PDP10 folks out there, "UnUsed Operations", later "Unimplemen= ted User Operations", op codes left intentionally undefined which when encountered in the instruction stream check to see whether there is a trap defined, so a system-style subroutine call. Opcodes 001-037 are avaiable to user programs, while 040-077 are defined for the operating system. --===============2564487248644357352==-- From imp@bsdimp.com Thu Apr 3 22:52:42 2025 From: Warner Losh To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 16:52:25 -0600 Message-ID: In-Reply-To: <1611713586.695160.1743717058727@email.ionos.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1884556923976565376==" --===============1884556923976565376== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On Thu, Apr 3, 2025, 3:51 PM Will Cooke via cctalk wrote: > > > > On 04/03/2025 5:37 PM EDT Chuck Guzis via cctalk > wrote: > > > > > > On 4/3/25 14:21, John Foust via cctalk wrote: > > > At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: > > > > > In another task where I wanted to quickly generate a text-based > > > profile of a computer's specifications and components, it was very > > > helpful in writing a bunch of PowerShell. Did it hallucinate? > > > Perhaps once out of several dozen things I asked it, and in that > > > case, it was easy to see that the two clauses of the if-then were > > > the same. > > > > Interesting. I got no help at all from ChatGPT when working through > > some IBM 7090 code. > > > > --Chuck > > > My experience has been much like John's. In my company of 10,000 ish > employees, the entire company is "strongly encouraged" to use various "AI" > tools made available. The encouragement comes directly from the CEO (and > all his minions echo it) during his monthly video addresses. > So, all of us who write code have copilot licenses and they actually track > how much we use it (can you say layoff? I knew you could.) What I have > found is that the short suggestions of a half dozen lines or more are often > pretty good. It's the bad ones I have to fight the system to NOT take that > eat up the time. I usually could have just written those half dozen lines > faster. But sometimes it helps a lot. Apparently it tracks names and kind > find the correct variable or constant faster than I could. A couple of > coworkers have given a good description: good for boilerplate code. > That's what I've found too. Generate the boilerplate for me: not very creative but usuall 90+% right for code I'll be rototilling anyway. Small code: usually ok. Generate about 10-50 lines it's ok. But much more than that and the errors are too high to be worth it. Debugging time becomes much higher than the just write it from scratch time. Small snippets are also easier to catch errors on too. It's not terrible. On par with autocomplete emacs macros I've sometimes written but with less effort. But it's not great either, at least for the code I write. Warner As for chatgpt not doing well, I suspect that is largely due to it being a > general purpose "question answerer" rather than a tool specifically for > programming. I know of at least one person who did, however, get hired > based mostly on code written by chatgpt. But he didn't last long. > > Will > --===============1884556923976565376==-- From elson@pico-systems.com Thu Apr 3 23:12:18 2025 From: Jon Elson To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 18:12:11 -0500 Message-ID: In-Reply-To: <20250403212206.7E27286196@classiccmp.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8884742808301782919==" --===============8884742808301782919== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On 4/3/25 16:21, John Foust via cctalk wrote: > At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: >> Apparently, some think that within 10 years, AI will replace doctors and >> teachers: > It's one thing to say that AI methods have been shown to give better > diagnoses in some situations than the humans, it's quite another to > suggest we won't need doctors. In my neck of the woods, even doctors > have been greatly supplanted by physician assistants. > > I'm as skeptical as they come, and I have plenty of criticisms of AI > as implemented today, but I've also been confounded to discover how > useful it can be when programming. It's often better than googling and > copy-and-pasting from Stackoverflow. > I am also skeptical.  I am a minor developer on the LinuxCNC project and somebody suggested getting chatGPT to come up with a script for setting the I?O side of that up.  Since this is a VERY niche project, I didn't expect it to do much.  I was amazed that it created a script that a cursory scan indicated it might actually work! Our IT guy at work swears by chatGPT.  He was trying to debug some issues with VirtualBox setup after a kernel upgrade on my Linux desktop.  (My fix is to disable ALL updates).  Anyway, he was going crazy, and wasted about TWO DAYS trying to fix it!  I went straight to the Oracle web site and downloaded the update file, and then typed the commands exactly as shown on their update page, and it worked perfectly!  I am guessing that chatGPT was making a response based on previous versions of the software, and those were just wrong for the latest version. So, I've seen both. As for PAs, my regular doctor was out of town, I had a rash on my side and went to an urgent care place, the PA there totally misdiagnosed it, and it got worse.  Then, I went to a dermatologist, he took a sample of scrapings off the rash, diagnosed it correctly, and the prescription solved it.  Not sure my regular doctor would have been able to diagnose it either. Jon --===============8884742808301782919==-- From elson@pico-systems.com Thu Apr 3 23:14:47 2025 From: Jon Elson To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 18:14:39 -0500 Message-ID: <2b4b7493-7c29-057a-6973-444ec60af1cc@pico-systems.com> In-Reply-To: <8b13441b-ed6a-476f-906f-5712906874ff@sydex.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1415085477159601357==" --===============1415085477159601357== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/3/25 16:37, Chuck Guzis via cctalk wrote: > On 4/3/25 14:21, John Foust via cctalk wrote: >> At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: >> In another task where I wanted to quickly generate a text-based >> profile of a computer's specifications and components, it was very >> helpful in writing a bunch of PowerShell. Did it hallucinate? >> Perhaps once out of several dozen things I asked it, and in that >> case, it was easy to see that the two clauses of the if-then were >> the same. > Interesting. I got no help at all from ChatGPT when working through > some IBM 7090 code. Well, that likely dates WAY before the large language model has seen. Jon --===============1415085477159601357==-- From cclist@sydex.com Thu Apr 3 23:23:40 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 23:23:31 +0000 Message-ID: <114c29a9-a053-47bb-89f7-2c9c17e928ad@sydex.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8602006626672639290==" --===============8602006626672639290== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On 4/3/25 16:12, Jon Elson via cctalk wrote: > As for PAs, my regular doctor was out of town, I had a rash on my side > and went to an urgent care place, the PA there totally misdiagnosed it, > and it got worse.  Then, I went to a dermatologist, he took a sample of > scrapings off the rash, diagnosed it correctly, and the prescription > solved it.  Not sure my regular doctor would have been able to diagnose > it either. Like every other human endeavor, there are good and not-so-good professionals. I've gotten somewhat better attention from a DO than an MD, but that could be the luck of the draw. Being a cancer patient with a rare sarcoma, I've seen a *lot* of doctors lately--with more to come. --Chuck --===============8602006626672639290==-- From wayne.sudol@hotmail.com Thu Apr 3 23:36:18 2025 From: Wayne S To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 23:36:09 +0000 Message-ID: In-Reply-To: <114c29a9-a053-47bb-89f7-2c9c17e928ad@sydex.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4012683631045297910==" --===============4012683631045297910== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable I=E2=80=99ve not had good luck with any PA=E2=80=99s so I won=E2=80=99t see t= hem. Their diagnosis is supposed to be reviewed/approved by a real Doctor, but I d= on=E2=80=99t think that happens like it=E2=80=99s supposed to. =20 Sent from my iPhone > On Apr 3, 2025, at 16:23, Chuck Guzis via cctalk = wrote: >=20 > =EF=BB=BFOn 4/3/25 16:12, Jon Elson via cctalk wrote: >=20 >> As for PAs, my regular doctor was out of town, I had a rash on my side >> and went to an urgent care place, the PA there totally misdiagnosed it, >> and it got worse. Then, I went to a dermatologist, he took a sample of >> scrapings off the rash, diagnosed it correctly, and the prescription >> solved it. Not sure my regular doctor would have been able to diagnose >> it either. >=20 > Like every other human endeavor, there are good and not-so-good > professionals. I've gotten somewhat better attention from a DO than an > MD, but that could be the luck of the draw. >=20 > Being a cancer patient with a rare sarcoma, I've seen a *lot* of doctors > lately--with more to come. >=20 > --Chuck >=20 --===============4012683631045297910==-- From doc@vaxen.net Fri Apr 4 02:29:43 2025 From: Doc Shipley To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Thu, 03 Apr 2025 21:29:34 -0500 Message-ID: <543aacaf-ab58-429c-bd24-982dffaddc11@vaxen.net> In-Reply-To: <8b13441b-ed6a-476f-906f-5712906874ff@sydex.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1910700942223218008==" --===============1910700942223218008== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/3/25 16:37, Chuck Guzis via cctalk wrote: > On 4/3/25 14:21, John Foust via cctalk wrote: >> At 10:22 PM 4/1/2025, Chuck Guzis via cctalk wrote: > >> In another task where I wanted to quickly generate a text-based >> profile of a computer's specifications and components, it was very >> helpful in writing a bunch of PowerShell. Did it hallucinate? >> Perhaps once out of several dozen things I asked it, and in that >> case, it was easy to see that the two clauses of the if-then were >> the same. > > Interesting. I got no help at all from ChatGPT when working through > some IBM 7090 code. I have a friend who's an EE and taking advanced math and statistics courses at his university. He's middle aged, a brilliant engineer, and blessed with at least some common sense. He uses ChatGPT and a couple of other free AI services to write a lot of code for his classwork (with his instructors' blessing), and we've talked a lot about using that effectively. The short version is that ChatGPT works well for writing functions and snippets - small, mostly linear pieces - but not complex processes. And more importantly, you have to be able to write what you're asking for, AND VALIDATE the output. Finally, he says it's a lot like a web search. The query is key to getting correct results. The ability to diagnose incorrect results and modify the query is a determining factor. Doc --===============1910700942223218008==-- From jfoust@threedee.com Fri Apr 4 13:20:14 2025 From: John Foust To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Fri, 04 Apr 2025 08:19:52 -0500 Message-ID: <20250404132008.7AAEF8183F@classiccmp.org> In-Reply-To: <543aacaf-ab58-429c-bd24-982dffaddc11@vaxen.net> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3408868489609764760==" --===============3408868489609764760== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable At 09:29 PM 4/3/2025, Doc Shipley via cctalk wrote: >The short version is that ChatGPT works well for writing functions and snipp= ets - small, mostly linear pieces - but not complex processes. And more impo= rtantly, you have to be able to write what you're asking for, AND VALIDATE th= e output. Sounds like he needs to write longer, more complex queries. It's perfectly possible to hand it nine pages of description of what you want. To keep this slightly more on-topic, if there is demand for AI to generate or explain code of old dialects of BASIC, who out there is training a model on old BASIC source code? - John --===============3408868489609764760==-- From spectre@floodgap.com Fri Apr 4 18:01:14 2025 From: Cameron Kaiser To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Fri, 04 Apr 2025 10:55:58 -0700 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3735843374430360115==" --===============3735843374430360115== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable > As for PAs, my regular doctor was out of town, I had a rash on my side and = went > to an urgent care place, the PA there totally misdiagnosed it, and it got > worse.=C2=A0 Then, I went to a dermatologist, he took a sample of scrapings= off the > rash, diagnosed it correctly, and the prescription solved it.=C2=A0 Not sur= e my > regular doctor would have been able to diagnose it either. Admittedly, the fact he scraped it and got a sample is likely *why* he got it right. When in doubt about a rash, get a chunk of it. I haven't been in gener= al practice in over a decade but I never referred until I had a pathology result. On the other hand, general medicine and family medicine practices have so little time for visits now. I don't miss that grind. I don't think AI will do a good job of taking biopsies ... --=20 ------------------------------------ personal: http://www.cameronkaiser.com/ = -- Cameron Kaiser * Floodgap Systems * www.floodgap.com * ckaiser(a)floodgap.c= om -- Premature optimization is the root of all evil. -- Donald Knuth ----------= -- --===============3735843374430360115==-- From Flash688@flying-disk.com Fri Apr 4 18:07:39 2025 From: Alan Frisbie To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Fri, 04 Apr 2025 11:00:11 -0700 Message-ID: In-Reply-To: <174378601050.1244.18326789503014413675@classiccmp.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0576217287173813465==" --===============0576217287173813465== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Bob Grabau write: > As my memory serves, there was a class given by the Southern > California Computer Society (SCCS) in which the disassembled the > Altair Basic (not sure if it was the 4k or 8k version) and used the > output of that disassembly for the class. There was a guy who had the > complete annotated (by the class) of the source as printed out copies > in his trunk, which he just handed out to anyone that asked for it. > This was somewhere between 1975-1978 (76-77 most likely) when I was a > member of SCCS. I was part of that disassembly effort and remember it well! I'm pretty sure I still have my copy of it stashed away here. It was a lot of fun. I had been a very early (1974) user of the 8080 at NCR, and this gave me a chance to contribute to the knowledge base. One thing I intend to do with this listing is find a piece of code I worked to disassemble, and read the comments. As I recall, it was part of some error handling. It consisted of a string of three-byte instructions that did nothing important, but if you jumped into the second byte of one, it would (as I recall) act as a two-byte instruction and load a register with an error code. After executing that 2/3 instruction, it fell into the remaining string of three-byte instructions which did nothing of interest. At the end, it would take the value that had been loaded earlier and use it. I was simultaneously impressed and appalled by this space-saving coding technique. I'm disappointed that two printer pages are combined into a single PDF page, as it makes it a bit difficult to read. Still, it is a great window into the minds of Bill, Paul, and Monte. Alan Frisbie --===============0576217287173813465==-- From bill.gunshannon@hotmail.com Fri Apr 4 19:16:33 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Fri, 04 Apr 2025 15:15:56 -0400 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2751593759041377350==" --===============2751593759041377350== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On 4/4/2025 2:00 PM, Alan Frisbie via cctalk wrote: > Bob Grabau write: > > > As my memory serves, there was a class given by the Southern > > California Computer Society (SCCS) in which the disassembled the > > Altair Basic (not sure if it was the 4k or 8k version) and used the > > output of that disassembly for the class. There was a guy who had the > > complete annotated (by the class) of the source as printed out copies > > in his trunk, which he just handed out to anyone that asked for it. > > This was somewhere between 1975-1978 (76-77 most likely) when I was a > > member of SCCS. > > I was part of that disassembly effort and remember it well!  I'm pretty > sure I still have my copy of it stashed away here.  It was a lot of > fun.  I had been a very early (1974) user of the 8080 at NCR, and > this gave me a chance to contribute to the knowledge base. > > One thing I intend to do with this listing is find a piece of code > I worked to disassemble, and read the comments. > > As I recall, it was part of some error handling.  It consisted of a > string of three-byte instructions that did nothing important, but if you > jumped into the second byte of one, it would (as I recall) act as a > two-byte instruction and load a register with an error code.  After > executing that 2/3 instruction, it fell into the remaining string of > three-byte instructions which did nothing of interest.   At the end, > it would take the value that had been loaded earlier and use it. > > I was simultaneously impressed and appalled by this space-saving > coding technique. It was quite common back in the day. :-) > > I'm disappointed that two printer pages are combined into a single > PDF page, as it makes it a bit difficult to read.   Still, it is a > great window into the minds of Bill, Paul, and Monte. > They sold a book containing a complete, commented dis-assembly of BASIC on the TRS-80 Model 3. I still have my copy of the original book and a Xerox of it my father did for some reason. bill --===============2751593759041377350==-- From elson@pico-systems.com Sat Apr 5 01:25:00 2025 From: Jon Elson To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Fri, 04 Apr 2025 20:24:53 -0500 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3582415546651589706==" --===============3582415546651589706== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On 4/4/25 12:55, Cameron Kaiser via cctalk wrote: >> As for PAs, my regular doctor was out of town, I had a rash on my side and= went >> to an urgent care place, the PA there totally misdiagnosed it, and it got >> worse.=C2=A0 Then, I went to a dermatologist, he took a sample of scraping= s off the >> rash, diagnosed it correctly, and the prescription solved it.=C2=A0 Not su= re my >> regular doctor would have been able to diagnose it either. > > Admittedly, the fact he scraped it and got a sample is likely *why* he got = it > right. When in doubt about a rash, get a chunk of it. I haven't been in gen= eral > practice in over a decade but I never referred until I had a pathology resu= lt. > On the other hand, general medicine and family medicine practices have so > little time for visits now. I don't miss that grind. Right, I don't think my internist would have had the=20 reagents or whatever on hand to identify the cause of the=20 rash, but I think he would have recognized it as an=20 infection.=C2=A0 The PA gave me some steroid cream which was=20 totally the wrong thing to do. > I don't think AI will do a good job of taking biopsies ... > Right, some thing need hands or eyes right on the scene. Jon --===============3582415546651589706==-- From mphuff@gmail.com Sat Apr 5 02:37:45 2025 From: Michael Huff To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Fri, 04 Apr 2025 18:37:27 -0800 Message-ID: In-Reply-To: <20250404132008.7AAEF8183F@classiccmp.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2614744763343648355==" --===============2614744763343648355== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable I've played with using ChatGPT to write code for older things (quickbasic, 1990's C++, stuff like that). In my experience it gets confused and gives you snippets that has features from later, modern languages. I'm far from an expert but it feels to me like it gets confused during processing about what to use as a source when giving it's answer. So based on that, I'd say that the training wouldn't help a whole lot. On Fri, Apr 4, 2025 at 10:06=E2=80=AFAM John Foust via cctalk wrote: > At 09:29 PM 4/3/2025, Doc Shipley via cctalk wrote: > >The short version is that ChatGPT works well for writing functions and > snippets - small, mostly linear pieces - but not complex processes. And > more importantly, you have to be able to write what you're asking for, AND > VALIDATE the output. > > Sounds like he needs to write longer, more complex queries. It's perfectly > possible to hand it nine pages of description of what you want. > > To keep this slightly more on-topic, if there is demand for AI to generate > or explain code of old dialects of BASIC, who out there is training > a model on old BASIC source code? > > - John > > --===============2614744763343648355==-- From bfranchuk@jetnet.ab.ca Sat Apr 5 03:15:39 2025 From: ben To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Fri, 04 Apr 2025 21:15:24 -0600 Message-ID: <8fd4906f-487c-4ea9-b868-7041b746a9e6@jetnet.ab.ca> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3564739437702425365==" --===============3564739437702425365== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 2025-04-04 8:37 p.m., Michael Huff via cctalk wrote: > I've played with using ChatGPT to write code for older things (quickbasic, > 1990's C++, stuff like that). In my experience it gets confused and gives > you snippets that has features from later, modern languages. I'm far from > an expert but it feels to me like it gets confused during processing about > what to use as a source when giving it's answer. > > So based on that, I'd say that the training wouldn't help a whole lot. I thought FORTRAN IV was the portable programing language. They have talked about having smarter high level programing languages for years. Has that gotten anywhere? --===============3564739437702425365==-- From cclist@sydex.com Sat Apr 5 03:44:18 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 03:44:08 +0000 Message-ID: In-Reply-To: <8fd4906f-487c-4ea9-b868-7041b746a9e6@jetnet.ab.ca> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2051405894073700615==" --===============2051405894073700615== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/4/25 20:15, ben via cctalk wrote: > I thought FORTRAN IV was the portable programing language. > They have talked about having smarter high level programing languages > for years. Has that gotten anywhere? Back in the heyday of FORTRAN, the universe of architectures was a lot more diverse and foreign to languages such as C. Non-binary (decimal) numeric representations, Binary ones' complement math, vendor-unique character sets (it's why FORTRAN (and COBOL) is written using a very small common character set)--and lack of character-handling operations, as well as Boolean functions. I think that the original PALASM was written in "portable" FORTRAN. One of the more common ways to start a "portable" program was to READ a card with the character set punched onto it in A1 format. You manipulated characters by referring to their positions in the alpha A1 array. --Chuck --===============2051405894073700615==-- From brian.cockburn.1959@gmail.com Sat Apr 5 12:35:38 2025 From: Brian Cockburn To: cctalk@classiccmp.org Subject: [cctalk] Re: Altair BASIC Source Code released Date: Sat, 05 Apr 2025 23:35:29 +1100 Message-ID: <575220fa-e166-48c7-9cbe-16c855cc5cb5@gmail.com> In-Reply-To: <311BBE74-F6D1-4312-A4FB-14A600FD4AB8@gmail.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5809902796799397188==" --===============5809902796799397188== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Hi, (First post, so go easy on me.) Perhaps what we have is not so much the release of the 8080 instructions, but the comments and, for what it's worth, the variable and storage names. This surely gives an insight that a disassembly, even an annotated one, just can't give? Cheers, Brian. --===============5809902796799397188==-- From bill.gunshannon@hotmail.com Sat Apr 5 14:03:43 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 10:03:19 -0400 Message-ID: In-Reply-To: <8fd4906f-487c-4ea9-b868-7041b746a9e6@jetnet.ab.ca> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3875643402946185833==" --===============3875643402946185833== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit On 4/4/2025 11:15 PM, ben via cctalk wrote: > On 2025-04-04 8:37 p.m., Michael Huff via cctalk wrote: >> I've played with using ChatGPT to write code for older things >> (quickbasic, >> 1990's C++, stuff like that). In my experience it gets confused and gives >> you snippets that has features from later, modern languages. I'm far from >> an expert but it feels to me like it gets confused during processing >> about >> what to use as a source when giving it's answer. >> >> So based on that, I'd say that the training wouldn't help a whole lot. > > I thought FORTRAN IV was the portable programing language. > They have talked about having smarter high level programing languages > for years. Has that gotten anywhere? I never thought of Fortran of being portable by design. It may be fairly portable just because of the simplicity of the language. I'll let you know, I am about to try moving a program that ran on TOPS-10 and IBM MTS to Microsoft Fortran-80. :-) The truly portable language was COBOL. :-) bill --===============3875643402946185833==-- From cclist@sydex.com Sat Apr 5 15:09:08 2025 From: Chuck Guzis To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 15:08:57 +0000 Message-ID: <327b3a74-5ce6-42de-afaf-7c2cc415312d@sydex.com> In-Reply-To: =?utf-8?q?=3CLV8P221MB14697C24E69E81219A310D5FEDA82=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7051191428567255250==" --===============7051191428567255250== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On 4/5/25 07:03, Bill Gunshannon via cctalk wrote: > I never thought of Fortran of being portable by design. It may > be fairly portable just because of the simplicity of the language. > I'll let you know, I am about to try moving a program that ran on > TOPS-10 and IBM MTS to Microsoft Fortran-80.  :-) I did something similar some 50 years ago. Took the PDP-10 "Colossal Cave/Adventure" source to CDC 6000 FORTRAN running under SCOPE. The part that involved the most labor was conversion of the source code tape that used the TOPS-10 convention of 5 7-bit ASCII in a 36 bit word to CDC 6 bit Display code. Conversion of the FORTRAN dialect was fairly trivial; the most effort involved re-implementing the SAVE command (CDC SCOPE did not have a simple method for saving core images and restarting them). The result ran almost from the first try. > The truly portable language was COBOL.  :-) 50 years ago, COBOL (and FORTRAN) standardization was a loose affair. Many smaller systems simply lacked COBOL (was there a 1401 COBOL?). Language features were removed as the machine architecture dictated. For example, contrast 1960s IBM S/360 USA "BASIC" FORTRAN with, say UNIVAC 1108 FORTRAN-V. Going from the small (no logical IF, etc.) IBM dialect to the UNIVAC one would have been pretty simple; the other direction, not so much. I recall that DOS/360 COBOL as released lacked ISAM--the statements could be compiled, but no code was generated. Instead, IBM provided a bunch of library routines that were invoked with the "ENTER LINKAGE" statement. --Chuck --Chuck --===============7051191428567255250==-- From bfranchuk@jetnet.ab.ca Sat Apr 5 17:53:18 2025 From: ben To: cctalk@classiccmp.org Subject: [cctalk] Re: AI taking over the world! Date: Sat, 05 Apr 2025 11:53:10 -0600 Message-ID: <49488267-eed6-47db-8ea5-6f4cb2565cfc@jetnet.ab.ca> In-Reply-To: <327b3a74-5ce6-42de-afaf-7c2cc415312d@sydex.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6117534483018275381==" --===============6117534483018275381== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Perhaps it is time to look at AI, 50 years ago. Byte vol 3 jan - brains of men and machines. Have we gotten farther in better computer tech? Ben. GO ANALOG - GET YOUR BRAIN IN A BOTTLE TODAY 99 cent special, SEE 'EVIL MINIONS R US'. --===============6117534483018275381==-- From glg@grebus.com Sat Apr 5 23:48:10 2025 From: Gary Grebus To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 19:41:57 -0400 Message-ID: <96f61abe-840f-4cfb-b33d-9f34635b252d@grebus.com> In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8794702499977679768==" --===============8794702499977679768== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit In those days, FORTRAN IV was handy as a "portable" language just because it was the one language (other than COBOL) available *everywhere*. It could be used as a sort of "high level assembler" too. My first job out of college was working on a large database system. It was written using a pre-processor (think of RATFOR) and a bit of per-platform assembler for things that couldn't be done in standard FORTRAN (e.g. random access files, OS calls). It was a real, high performance database system that ran on CDC, UNIVAC, IBM 370, Xerox SIGMA, PDP-10/20, and VAX. Each new platform usually turned up some minor quirks. We always said there were no portable programs, only programs that had been ported. Gary On 4/4/25 23:44, Chuck Guzis via cctalk wrote: > On 4/4/25 20:15, ben via cctalk wrote: > >> I thought FORTRAN IV was the portable programing language. >> They have talked about having smarter high level programing languages >> for years. Has that gotten anywhere? > > Back in the heyday of FORTRAN, the universe of architectures was a lot > more diverse and foreign to languages such as C. Non-binary (decimal) > numeric representations, Binary ones' complement math, vendor-unique > character sets (it's why FORTRAN (and COBOL) is written using a very > small common character set)--and lack of character-handling operations, > as well as Boolean functions. > > I think that the original PALASM was written in "portable" FORTRAN. One > of the more common ways to start a "portable" program was to READ a card > with the character set punched onto it in A1 format. You manipulated > characters by referring to their positions in the alpha A1 array. > > --Chuck > > > > --===============8794702499977679768==-- From cisin@xenosoft.com Sun Apr 6 00:23:23 2025 From: Fred Cisin To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 17:23:16 -0700 Message-ID: In-Reply-To: <96f61abe-840f-4cfb-b33d-9f34635b252d@grebus.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4724021771165866358==" --===============4724021771165866358== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable > In those days, FORTRAN IV was handy as a "portable" language just because i= t=20 > was the one language (other than COBOL) available *everywhere*. It could b= e=20 > used as a sort of "high level assembler" too. "FORTRAN --"the infantile disorder"--, by now nearly 20 years old, is=20 hopelessly inadequate for whatever computer application you have in mind=20 today: it is now too clumsy, too risky, and too expensive to use." - "How do we tell truths that might hurt?" - Edsger W.Dijkstra, 18 June 1975 "The use of COBOL cripples the mind; its teaching should, therefore, be=20 regarded as a criminal offence." - "How do we tell truths that might hurt?" - Edsger W.Dijkstra, 18 June 1975 Dijkstra had things to say about many languages. In 1975, . . . Fortran77 or Fortran90 did fix a few things, but not necessarily the right=20 ones. Who was who said that FORTRAN was "more portable than syphilis"? --===============4724021771165866358==-- From cisin@xenosoft.com Sun Apr 6 01:18:34 2025 From: Fred Cisin To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 18:18:28 -0700 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1529214854097694897==" --===============1529214854097694897== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit a friend asked me whether ChatGPT designed and planned DOGE ? --===============1529214854097694897==-- From bill.gunshannon@hotmail.com Sun Apr 6 02:32:24 2025 From: Bill Gunshannon To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sat, 05 Apr 2025 22:31:53 -0400 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============4720639285725876265==" --===============4720639285725876265== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit On 4/5/2025 8:23 PM, Fred Cisin via cctalk wrote: >> In those days, FORTRAN IV was handy as a "portable" language just >> because it was the one language (other than COBOL) available >> *everywhere*.  It could be used as a sort of "high level assembler" too. > > "FORTRAN --"the infantile disorder"--, by now nearly 20 years old, is > hopelessly inadequate for whatever computer application you have in mind > today: it is now too clumsy, too risky, and too expensive to use." > - "How do we tell truths that might hurt?" > - Edsger W.Dijkstra, 18 June 1975 > > "The use of COBOL cripples the mind; its teaching should, therefore, be > regarded as a criminal offence." > - "How do we tell truths that might hurt?" > - Edsger W.Dijkstra, 18 June 1975 > > > Dijkstra had things to say about many languages. > In 1975, . . . > Fortran77 or Fortran90 did fix a few things, but not necessarily the > right ones. > And it was comments like those that convinced me Dyjkstra was an idiot and I have never placed any value on anything he ever said. bill --===============4720639285725876265==-- From g4ajq1@gmail.com Sun Apr 6 11:50:27 2025 From: Nigel Johnson Ham To: cctalk@classiccmp.org Subject: [cctalk] Re: Why I am not worried about AI taking over the world! Date: Sun, 06 Apr 2025 07:50:02 -0400 Message-ID: <7e3e6911-9c6a-4a27-af37-540a99540c81@gmail.com> In-Reply-To: =?utf-8?q?=3CLV8P221MB1469F41BFDDC544F0162FA8AEDAB2=40LV8P221MB?= =?utf-8?q?1469=2ENAMP221=2EPROD=2EOUTLOOK=2ECOM=3E?= MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8772479102932821028==" --===============8772479102932821028== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit Dijkstra was my GOTO man for anything to do with computing! :-) Nigel On 2025-04-05 22:31, Bill Gunshannon via cctalk wrote: > > > On 4/5/2025 8:23 PM, Fred Cisin via cctalk wrote: >>> In those days, FORTRAN IV was handy as a "portable" language just >>> because it was the one language (other than COBOL) available >>> *everywhere*.  It could be used as a sort of "high level assembler" >>> too. >> >> "FORTRAN --"the infantile disorder"--, by now nearly 20 years old, is >> hopelessly inadequate for whatever computer application you have in >> mind today: it is now too clumsy, too risky, and too expensive to use." >> - "How do we tell truths that might hurt?" >> - Edsger W.Dijkstra, 18 June 1975 >> >> "The use of COBOL cripples the mind; its teaching should, therefore, >> be regarded as a criminal offence." >> - "How do we tell truths that might hurt?" >> - Edsger W.Dijkstra, 18 June 1975 >> >> >> Dijkstra had things to say about many languages. >> In 1975, . . . >> Fortran77 or Fortran90 did fix a few things, but not necessarily the >> right ones. >> > > And it was comments like those that convinced me Dyjkstra was an idiot > and I have never placed any value on anything he ever said. > > bill > -- Nigel Johnson, MSc., MIEEE, MCSE VE3ID/G4AJQ/VA3MCU Amateur Radio, the origin of the open-source concept! Skype: TILBURY2591 --===============8772479102932821028==-- From ard.p850ug1@gmail.com Sun Apr 6 18:06:35 2025 From: Tony Duell To: cctalk@classiccmp.org Subject: [cctalk] Philips P3800 key lock swtch Date: Sun, 06 Apr 2025 19:04:37 +0100 Message-ID: In-Reply-To: <67f2bc7e.050a0220.1684bc.5b5e.GMR@mx.google.com> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7424226891033523624==" --===============7424226891033523624== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Does anyone know anything about the key lock on the mains on/off switch of the P3800? I have one without a key. I can't identify the lock manufacturer (no markings on it at all) so I've not been able to get a blank to cut a replacement key. A friend who is a locksmith said she'd never seen anything like it. Any ideas who made the lock itself? Were all P3800 machines normally 'keyed alike' If so, a copy of an existing key (anyone have one?) would be a great help. Yes, I can trvially bypass the lock/switch mechanically or electrically. But I want to try to get this thing as original as possible. -tony --===============7424226891033523624==-- From drwho@virtadpt.net Sun Apr 6 21:02:16 2025 From: The Doctor To: cctalk@classiccmp.org Subject: [cctalk] Re: Philips P3800 key lock swtch Date: Sun, 06 Apr 2025 20:54:35 +0000 Message-ID: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============5972627521050148285==" --===============5972627521050148285== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable On Sunday, April 6th, 2025 at 11:04, Tony Duell via cctalk wrote: > Does anyone know anything about the key lock on the mains on/off > switch of the P3800? >=20 > I have one without a key. I can't identify the lock manufacturer (no > markings on it at all) so I've not been able to get a blank to cut a > replacement key. A friend who is a locksmith said she'd never seen > anything like it. Do you know what kind of lock it is? Pin tumbler? Wafer? Lever? Tubular? Warded? Disc? Sidebar? Can you see the edge of a pin from the front of the lock? Is there just one = or two? Can you post a picture of what you can see? It sounds old enough that it's unlikely to be a dimple locks. With a bit more information we might be able to deduce the type of lock. Fro= m that, the type of key. And from that, techniques to make replacement keys with app= ropriate bitting. And possibly advise on servicing the lock. Did your locksmith friend tell you any details she'd been able to suss out af= ter inspection? The Doctor [412/724/301/703/415/510] WWW: https://drwho.virtadpt.net/ Get thee down. Be thou funky. --===============5972627521050148285==--