Live data from Hacker News

Show HN: TetrisBench – Gemini Flash reaches 66% win rate on Tetris against Opus

tetrisbench.com

21–30 of 42 posts

Re: Show HN: TetrisBench – Gemini Flash reaches 66% win rate on Tetris against Opus

#25
post #20

Interesting but frustratingly vague on details. How exactly are the models playing? Is it using some kind of PGN equivalent in Tetris that represents a on-going game, passing an ASCII representation, encoding as a JSON structure, or just directly sending screenshots of the game to the various LLMs?

answered this in a comment above! It's not turn or visual layout based since LLMs are not trained that way. The representation is a JSON structure, but LLMs plug in algorithms and keeps optimizing it as the game state evolves

Thanks for the clarification! Kind of reminds me of the Brian Moore's AI clocks which uses several LLMs to continuously generate HTML/CSS to create an analog clock for comparisons.

https://clocks.brianmoore.com

Re: Show HN: TetrisBench – Gemini Flash reaches 66% win rate on Tetris against Opus

#27
post #20

Earlier quoted context omitted.

answered this in a comment above! It's not turn or visual layout based since LLMs are not trained that way. The representation is a JSON structure, but LLMs plug in algorithms and keeps optimizing it as the game state evolves

Thanks for the clarification! Kind of reminds me of the Brian Moore's AI clocks which uses several LLMs to continuously generate HTML/CSS to create an analog clock for comparisons. https://clocks.brianmoore.com

Wow this is incredible!!

Re: Show HN: TetrisBench – Gemini Flash reaches 66% win rate on Tetris against Opus

#28
post #20

Interesting but frustratingly vague on details. How exactly are the models playing? Is it using some kind of PGN equivalent in Tetris that represents a on-going game, passing an ASCII representation, encoding as a JSON structure, or just directly sending screenshots of the game to the various LLMs?

answered this in a comment above! It's not turn or visual layout based since LLMs are not trained that way. The representation is a JSON structure, but LLMs plug in algorithms and keeps optimizing it as the game state evolves

I suppose you could argue about whether it's an LLM at that point but vision is a huge part of frontier models now, no?

Re: Show HN: TetrisBench – Gemini Flash reaches 66% win rate on Tetris against Opus

#29
post #2

It would be more interesting to make it build a chess engine and compare it against Stockfish. The chess engine should be a standalone no-dependencies C/C++ program that fits in NNN lines of code.

oh that is super interesting. ty for the idea!

Re: Show HN: TetrisBench – Gemini Flash reaches 66% win rate on Tetris against Opus

#30
post #7

Earlier quoted context omitted.

The worst thing is that the delayed auto shift is slightly off and it messes my finesse. (I used to play competitive tetris as well, but between getting older -> worse reflexes and vision problems I can't really play anymore. Weirdly, finesse muscle memory is still working.) I don't think the goal is to make a PvP simulator, it would be too easy to cheese or do weird strategies. It's mostly for LLMs to play.

Hello fellow Tetris nerd with a -sort username :) On the topic of reflexes decaying (I'm getting there, in my late 30s): Have you played Stackflow? It's a number go up roguelite disguised as an arcade brick stacking game, but the gravity is low enough that it is effectively turn based. More about 'deck' building, less about chaining PCs and C-Spins.

Stackflow looks nice! I'm a Balatro fan and I didn't know about this variant.

By the way, kudos on your feedback. If I was OP, I would've been honored to get that type of fine-tuning comments.

Post reply on HN