This will be a weird rant, but the dialogue here is a perfect example of how SOTA models are so heavily tuned towards programming and "solving tasks" that they're useless at almost everything else - especially creative tasks.

"Coming for you, Crimson!"

"You'll never catch me alive, Azure!"

That's why nobody has been able to stick these things in a video game successfully, even though it seems like the tech is a perfect match.

It's all a game to them. They aren't afraid for their lives. Those are not the words of little pixel people fighting to the death, those are AI abominations making "tool calls", LARPing as little pixel people fighting to the death.

I'm 100% serious when I say that you would've gotten cooler outputs with a GPT 3.5-era model, once you managed to beat it into producing structured output. Llama 2 would be giving the other agent a heartwarming story about how if it kills it there would be nobody to take care of its grandma or whatever, and the other agent would probably spare it.

This has been an annoyance of mine for a while - the output is just so bland and devoid of soul. I feel like we would've found a lot of cool usecases for LLMs, had we not completely maimed their output in the pursuit of getting them to output 3% better TypeScript.

Fun, but considering this puts `claude-sonnet-5` at the first place isn't it a little... iffy when it comes to measuring intelligence?

Unusable website on Android running Chrome latest (can't scroll)

Since the page exposes frame-by-frame playback, a shareable replay link would make it easier to compare decisions across the four models.

Code link didn't work for me.

On mobile, I don't have enough room to scroll the background so I got stuck in a long text box.