[cheema33]

“Of all the points the other side makes, this one seems the most incoherent. Code is deterministic, AI isn’t. We don’t have to look at assembly, because a compiler produces the same result every time.”

This is a valid argument. However, if you create test harnesses using multiple LLMs validating each other’s work, you can get very close to compiler-like deterministic behavior today. And this process will improve over time.

[hakunin]

It helps, but it doesn't make it deterministic. LLMs could all be misled together. A different story would be if we had deterministic models, where the exact same input always results in the exact same output. I'm not sure why we don't try this tbh.

[verdverm]

I've been wondering if there are better random seeds, like how there are people who hunt for good seeds in Minecraft

[exe34]

it's literally just setting T=0. except they are not as creative then. they don't explore alternative ideas from the mean.

[hakunin]

Are you sure that it’s T=0. My comment’s first draft said “it can’t just be setting temp to zero can it?” But I felt like T is not enough. Try running the same prompt in new sessions with T=0, like “write a poem”. Will it produce the same poem each time? (I’m not where I can try it currently).

[otabdeveloper4]

> just add more magic turtles to the stack, bro

You're just amplifying hallucination and bias.