VitorPamplona on Nostr: You gotta give them guardrails. It's like AI in chess. Engines work because the game ...

You gotta give them guardrails. It's like AI in chess. Engines work because the game has a limited rule set and can explore possibilities ina closed space. When you are talking to an LLM you are *defining those rules of that "game"* for each session. You are literally making the game as you go. If the "game" is small enough, LLMs work. If it is too big or too undefined, there won't be enough tokens to do well.

quoting
nevent1q…fequ

I'm starting to realize that LLMs are good at thinking at a very high architectural level or a very low implementation level, but not so good at bridging the gap.