[viapivov]

I wonder how do people use LLMs so it does not hallucinates. Like 90% of the time the code is impeccable, but the remaining 10%... Let's say I determine the expertise by how well do people act of these 10%. For me, the first pillar is still there, but not in a good condition

[naveen99]

Just pretend you are working with a buggy api with poor misleading documentation. LOL Check your assumptions.

[Lionga]

Easy just add "Make no mistakes" to the proompt, clear skill issue.

In reality people who use LLMs so it does not hallucinate are the ones that just have to little knowledge to actually see when it does, because LLMs do and they always will. That is the only thing you can get with a stochastic word predictor.