Building LLM Applications for Production

Re:Building LLM Applications for Production by visarga on Friday April 14, 2023 @03:56AM (#35566724)

In open-book mode it does not hallucinate. That only happens in closed-book mode. So if you put a piece of text in the prompt you can trust the summary will be factual. You can also use it for information extraction - text to JSON.

[ Parent | on HN ]

Re:Building LLM Applications for Production by layer8 on Friday April 14, 2023 @07:16AM (#35568142)

What are you basing this assessment on? My understanding is that it can in principle still hallucinate, though with a lower probability.

[ Parent | on HN ]

Re:Building LLM Applications for Production by visarga on Friday April 14, 2023 @01:14PM (#35571989)

I experimented on the task of information extraction with GPT3 and 4.

[ Parent | on HN ]

Re:Building LLM Applications for Production by goatlover on Friday April 14, 2023 @02:23PM (#35572933)

I've had it hallucinate with text I've fed it. More so with 3.5 than 4, but it has happened.

[ Parent | on HN ]