Notice. New forum software under development. It's going to miss a few functions and look a bit ugly for a while, but I'm working on it full time now as the old forum was too unstable. Couple days, all good. If you notice any issues, please contact me.
|
Forum Index : Microcontroller and PC projects : ChatGPT conversation anyone?
Page 1 of 4 | |||||
Author | Message | ||||
Malibu Senior Member Joined: 07/07/2018 Location: AustraliaPosts: 228 |
A quote from Grogster from This thread... Just for my own look-see on ChatGPT, I thought I'd give a shot and see what happens (apologies for name-dropping here) I don't like hijacked threads, so I started a new one because I couldn't resist putting this stimulating conversation up for all to see The conversation went like this (with some truncated answers)... Q: What is MMBasic Q: who developed the mmbasic language Q: who is Michael Mastroianni Q: who developed the webmite operating system Q: was geoff graham the only one in webmite development Q: what did peter mather do for webmite development A bit of shakey ground so far, but ok, I'll accept it... .... so, now it gets a bit surreal... Q: who is grogster Q: who is malibu Q: are you sure about malibu ....conversation ends... WhAtThE.......? Laughed so hard at my new 'status', I nearly fell off the chair at this point! Now, I'm also really confused about who ANYbody is in this place! Please, feel free to add to the post with any other bizarre ChatGPT conversations you've had, this stuff is GOLD! John |
||||
Malibu Senior Member Joined: 07/07/2018 Location: AustraliaPosts: 228 |
right... I had to keep going because it was too much fun... Q: how can peter mather be malibu and grogster at the same time Q: are you sure of it this time Classic! John |
||||
Bryan1 Guru Joined: 22/02/2006 Location: AustraliaPosts: 1343 |
I wonder if that chat was Microsoft based |
||||
Grogster Admin Group Joined: 31/12/2012 Location: New ZealandPosts: 9305 |
LOL!!!! I'm flattered to be compared to Peter like that, but..... Smoke makes things work. When the smoke gets out, it stops! |
||||
Malibu Senior Member Joined: 07/07/2018 Location: AustraliaPosts: 228 |
I don't think so... It never told me to 'please wait' while the latest update was being installed. Nor did I need to have several coffees, a nanny-nap, walk the dog, mow the lawns and swear at the computer while I was waiting for an answer... 'fess up mate, who are you really??? (starting to wonder who I am too!) John |
||||
thwill Guru Joined: 16/09/2019 Location: United KingdomPosts: 4036 |
I'm Spartacus and so is my wife. Best wishes, Kirk Douglas Game*Mite, CMM2 Welcome Tape, Creaky old text adventures |
||||
Grogster Admin Group Joined: 31/12/2012 Location: New ZealandPosts: 9305 |
I don't think so... It never told me to 'please wait' while the latest update was being installed. Nor did I need to have several coffees, a nanny-nap, walk the dog, mow the lawns and swear at the computer while I was waiting for an answer... 'fess up mate, who are you really??? (starting to wonder who I am too!) ......I've said too much. Smoke makes things work. When the smoke gets out, it stops! |
||||
Mixtel90 Guru Joined: 05/10/2019 Location: United KingdomPosts: 6768 |
This is what makes AI so dangerous. It's not "Artificial Intelligence" at all, it's a "Simulation Of Intelligence". There is no intelligence there at all, artificial or otherwise. I've heard computers described as "lightning fast imbeciles" and that's still true, nothing has changed. They have improved in fields like data searching, comparison and handling but that doesn't mean that they are more intelligent. :) A computer system can only give a correct answer if it can be calculated mathematically. Even then the answer will be correct only if the question can only be taken one way. Any vagueness in the question and any answer can't possibly be considered to be reliable. "All right," said Deep Thought. "The Answer to the Great Question..." "Yes..!" "Of Life, the Universe and Everything..." said Deep Thought. "Yes...!" "Is..." said Deep Thought, and paused. "Yes...!" "Is..." "Yes...!!!...?" "Forty-two," said Deep Thought, with infinite majesty and calm.” ― Douglas Adams, The Hitchhiker’s Guide to the Galaxy Not bad after seven and a half million years calculation. Must have been Windows 1.1. . Edited 2024-09-07 16:57 by Mixtel90 Mick Zilog Inside! nascom.info for Nascom & Gemini Preliminary MMBasic docs & my PCB designs |
||||
JohnS Guru Joined: 18/11/2011 Location: United KingdomPosts: 3800 |
Thanks for posting that. I'm Spartacus... does that make me Tom's wife??? John |
||||
Bryan1 Guru Joined: 22/02/2006 Location: AustraliaPosts: 1343 |
Well I just tried chatgpt for the first time and got to ask 3 questions then it demanded my email address. So no thanks for this bot that just wants to spam my email |
||||
TassyJim Guru Joined: 07/08/2011 Location: AustraliaPosts: 6093 |
Judging by it's answers I am better of talking to myself. Only trust ChatGPT if you already know the answer... Jim (I think) VK7JH MMedit MMBasic Help |
||||
Grogster Admin Group Joined: 31/12/2012 Location: New ZealandPosts: 9305 |
So no thanks for this bot that just wants to spam my email Well, then....perhaps I was right in my ORIGINAL comment on the other thread! Smoke makes things work. When the smoke gets out, it stops! |
||||
Grogster Admin Group Joined: 31/12/2012 Location: New ZealandPosts: 9305 |
Jim (I think) That is brilliant. It should be on a T-shirt! ....could be extended to Alexa, Cortana and Siri. Edited 2024-09-07 17:53 by Grogster Smoke makes things work. When the smoke gets out, it stops! |
||||
lizby Guru Joined: 17/05/2016 Location: United StatesPosts: 3150 |
I haven't tried ChatGPT. I use perplexity.ai--but not when I think Iknow the right answer. When I can recognize answers which are clearly wrong, then sometimes I can drill down to get an at least plausible answer, with sources noted which I can follow for further clarification. But too many times the original answers are so clearly wrong that it would not be reasonable to ascribe intelligence to the source. I have found AI to be a valuable research tool to at least provide a path to an answer--far better than google search, which was itself far better than the old school method of having to go to the library to do research--or to have to take classes or find a mentor or apprentice oneself. PicoMite, Armmite F4, SensorKits, MMBasic Hardware, Games, etc. on fruitoftheshed |
||||
twofingers Guru Joined: 02/06/2014 Location: GermanyPosts: 1236 |
Kind regards BTW: I recently used ChatGPT to write batch files for unpacking nested RAR files with >100,000 files. It worked very well, although not on the first attempt. Later, ChatGPT wrote a batch file for sorting these files into folders with the appropriate initial letters. Example: (with comments in German) @echo off setlocal enabledelayedexpansion set "source_dir=C:\Pfad\zum\Quellverzeichnis" set "target_base_dir=C:\Pfad\zum\Zielverzeichnis" rem Kopiere alle Dateien rekursiv und ordne sie nach dem Anfangsbuchstaben for /r "%source_dir%" %%f in (*) do ( set "filename=%%~nxf" set "first_letter=!filename:~0,1!" rem Überprüfe, ob das Verzeichnis für den Buchstaben existiert if exist "%target_base_dir%\!first_letter!\" ( echo Kopiere %%f nach "%target_base_dir%\!first_letter!\" copy "%%f" "%target_base_dir%\!first_letter!\" >nul ) else ( echo Verzeichnis "%target_base_dir%\!first_letter!\" existiert nicht, Datei %%f wird übersprungen. ) ) echo. echo Vorgang abgeschlossen. pause I'm too old to remember the old DOS syntax. I found it helpful. BTW: Whenever I use ChatGPT I always feel a bit like Aladdin with his magic lamp. And I'm always waiting for the moment when it tells me that I've used up my three free wishes. ---------- Disclaimer: I own Microsoft stocks. Edited 2024-09-07 22:31 by twofingers causality ≠ correlation ≠ coincidence |
||||
PhenixRising Guru Joined: 07/11/2023 Location: United KingdomPosts: 856 |
Jim (I think) That is brilliant. It should be on a T-shirt! ....could be extended to Alexa, Cortana and Siri. I want that T-shirt along with the one "Never Trust the Autorouter" 1960's: "The government want to put recording devices in our homes!!!" 2024: "hey Alexa, is it ok to feed pancakes to my cat?" I always have my £60 Argos guitar, next to my desk. When I'm pondering something, I'll pick it up and take a stab at some obscure song, remembering about only 5 of the original lyrics and in a key that suits me. Before I know it, the original song shows-up as a suggestion on my YouTube...never fails |
||||
Gizmo Admin Group Joined: 05/06/2004 Location: AustraliaPosts: 5078 |
I use chat GPT daily for my work. As a software developer who works with well documented languages, it does a really good job. But anything less common, like the Micromite stuff, it will struggle. It is basically a human speech simulating front end to a lot of data, and the more data it has on a subject, the better is it. Get into less well documented subjects ( micromite for example ), and it starts to ramble on and make stuff up. It just doesn't have enough data, comparatively, to work with. I mean, a question about writing a simple loop in php, it would have millions of examples in its library, but maybe only a few dozen in PicoMite basic. I generally ask it a question, like how to do something using html, javascript, php, styles, and it usually gives me what I need first time. Its all about the question you ask. Occasionally I would then ask it to improve on something, or try a different approach. After that, I close the conversation and start a new conversation with new questions I have after testing and modifying the code it gave previously. By closing conversation earlier, I seam to avoid the incorrect data or hallucinations it generates in longer conversations. Glenn The best time to plant a tree was twenty years ago, the second best time is right now. JAQ |
||||
PhenixRising Guru Joined: 07/11/2023 Location: United KingdomPosts: 856 |
For code, I have had better results using: Phind |
||||
twofingers Guru Joined: 02/06/2014 Location: GermanyPosts: 1236 |
ChatGPT and Turing test: A Turing test of whether AI chatbots are behaviorally similar to humans causality ≠ correlation ≠ coincidence |
||||
pwillard Senior Member Joined: 07/06/2022 Location: United StatesPosts: 292 |
Here's your shirt... |
||||
Page 1 of 4 |
Print this page |