News for hackers. Stuff that matters.
Re:I played chess against ChatGPT-4 and lost by Buttons840 on Sunday March 19, 2023 @02:35AM (#35216583)
If you instruct it to use an alternate Chess notation, such as drawing an ASCII (or Unicode?) board every turn, can it do so? Does this effect it's play?

Instruct GTP4 to win the game and then crush it using Stockfish. Does it handle defeat gracefully?

Re:I played chess against ChatGPT-4 and lost by nhoughto on Sunday March 19, 2023 @02:45AM (#35216642)
Interesting idea, naively that seems possible based on other non chess example prompts I’ve seen. Would be a great way to understand it’s tracking of state throughout the game
Re:I played chess against ChatGPT-4 and lost by fenomas on Sunday March 19, 2023 @03:01AM (#35216715)
Not -4, but I tested the ASCII gameboard idea a bunch on ChatGPT (3.5) and could not make any headway. It would consistently announce a move and then print out the same gameboard it had been given (i.e. the game state before its move).

It sounds like -4 should be much better though; I wonder if having the gameboard would improve its gameplay?

Re:I played chess against ChatGPT-4 and lost by BoiledCabbage on Sunday March 19, 2023 @03:29AM (#35216828)
> I wonder if having the gameboard would improve its gameplay?

If it's an addition, then sure seems like it wouldn't hurt. If it's to replace the algebraic notation, then I'd say very likely worse. All of it's input / experiences w.r.t. chess have been in the language of algebraic chess notation. Swapping to only providing a game board would presumably be worse.

It'd be like if all of our interactions were in English in a latin script, and then someone replaced it with emojis. We don't think in emoji's it wouldn't help us, even if that's how they're used to thinking.

While we play chess by looking at the board state, it's likely little of chat-gpts input is in that format.

And the only other concern would be memory. Would it "forget" the prior moves. But I think not, simply because it receives the full game input each play simply by how GPT APIs work with passing in all prior tokens after each iteration.

Re:I played chess against ChatGPT-4 and lost by Buttons840 on Sunday March 19, 2023 @12:35PM (#35220716)
GTP playing chess through a visual (or visual-like) interface would be like us playing chess through notation. Same game, different view.

Of course, some humans can play chess quite well while blindfolded.

Re:I played chess against ChatGPT-4 and lost by charcircuit on Sunday March 19, 2023 @03:18AM (#35216779)
GPT4 can take image inputs
Re:I played chess against ChatGPT-4 and lost by _flux on Sunday March 19, 2023 @03:56AM (#35216950)
However, I believe this functionality has not yet been released to people outside OpenAI.
Re:I played chess against ChatGPT-4 and lost by WinstonSmith84 on Sunday March 19, 2023 @06:48AM (#35217755)
... and companies with privileged access (Microsoft, Midjourney V5, etc.)

There is a waiting list https://openai.com/waitlist/gpt-4-api

Re:I played chess against ChatGPT-4 and lost by mmahemoff on Sunday March 19, 2023 @03:21AM (#35216792)
Strangely, GPT4 refuses to draw a chessboard while earlier versions were up for it.

I do hope the chat interface improves soon. It seems like low hanging fruit compared to everything else that's been accomplished ... it will be like the jump from telnet/irc/ftp to web browsers.

Re:I played chess against ChatGPT-4 and lost by mmahemoff on Sunday March 19, 2023 @03:23AM (#35216799)
(I'm referring to ChatGPT's interface specifically, of course. Third party clients could use GPT4 to build a GUI chessboard.)