I've been hearing five years for decades; I'm confident that it will happen, but have no trust for promises about timing.
________________________________________ From: IBM Mainframe Discussion List <IBM-MAIN@LISTSERV.UA.EDU> on behalf of Bill Johnson <00000047540adefe-dmarc-requ...@listserv.ua.edu> Sent: Monday, September 4, 2023 1:20 PM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Re: Simple request from chatGPT to write assembler program. The formatting was perfect. The cut & paste wasn’t. Chatgpt has been available for what? 6 months? A year maybe? In 5 years, it’ll be 1000 times better. Sent from Yahoo Mail for iPhone On Monday, September 4, 2023, 1:04 PM, Matt Hogstrom <m...@hogstrom.org> wrote: Apart from the poor formatting I’ll share that ChatGPT does a poor job at assembler. Largely, I think, due to the lack of samples. If you look for Python, Node or other code examples it does an amazing job (although not perfect). I wouldn’t “blame” ChatGPT inasmuch as I’d understand that AI is nothing more at this point than a capability based on a large knowledge base of which Assembler is not much of one. What is more disturbing is the level of confidence portrayed when providing an answer which is clearly wrong. On Mon, Sep 4, 2023 at 09:57 Paul Gilmartin < 0000042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote: > On Mon, 4 Sep 2023 16:36:14 +0000, Bill Johnson wrote: > > >William: > > > >Write me an assembler program using high-level assembler for the > mainframe. > > > Fix your damn mailer, or throw it away and get one that works! > > In particular, do not use NBSP to format code samples. > > >Chatgpt: > > > >Certainly! Here’s a simple example of a mainframe assembly program > written in High-Level Assembler (HLASM) that reads two numbers from input > and prints their sum: > > PRINT NOGEN TITLE 'Simple Addition Program'** Define > storage for input numbers and result*NUM1 DS F First > input numberNUM2 DS F Second input numberRESULT DS > F Result of addition** Main program*MAIN C 0 > NUM1 Check if NUM1 is zero BE ZERO Branch to ZERO > if true** Read the first number from input* GET NUM1,NUMIN > Read NUM1 from input LA 0,NUM1 Load NUM1 into > register** Read the second number from input* GET NUM2,NUMIN > Read NUM2 from input A NUM1,NUM2 Add NUM1 and NUM2 > ST NUM1,RESULT Store the result in RESULT** Print the result* > PUT RESULT,NUMOUT Print the result** Terminate the program* > SR 15,15 Set return code to 0 BR 14 > Return to caller** Define input and output areas*NUMIN DC F'0' > Input buffer for numbersNUMOUT DC F'0' Output buffer > for resultZERO DC F'0' Constant zero END MAIN > End of program > >Please note that this is a simplified example for demonstration purposes. > In a real-world scenario, you would need to adapt this code to your > specific mainframe environment and requirements. Assembly language > programming can be quite complex, so make sure to consult the documentation > for your specific mainframe and assembler to ensure compatibility and > correctness. > > -- > gil > > ---------------------------------------------------------------------- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
