[gtirloni]

People are still figuring things out, there's a lot of wasted tokens, etc.

This is like complaining a student isn't as productive as a senior engineering.

I think we as an industry haven't even graduated to junior level when it comes to figuring our how to use AI to improve things.

[ozlikethewizard]

This is discussed in the article, and I think the author makes pretty reasonable arguments for why by nature we will not see the reliability of LLM usage improve. They also discuss what I agree as the more effective method of using an LLM is, as a feedback and refinement tool, not a decision maker.

[gtirloni]

> This is not a limitation that can be overcome by LLMs. Their generative value is in their unreliability. If you turn temperature down to zero, you get a deterministic machine - but you also break every meaningful application I know of in production.

This is not a reasonable argument. Setting the temperature down to zero does NOT give you a deterministic machine. And I have never seen that break any application in production, quite the contrary.

[oudlys]

By “break” I don’t mean “won’t function”. I mean “won’t deliver on their value proposition”. A functioning product is a necessary, but not a sufficient condition for technology to have utility. I would defend vigorously that the generative value in LLMs is derived from their unreliability. Which is what the argument ultimately rests on.