News for hackers. Stuff that matters.

A comment on Introducing Agents in Haystack: Make LLMs resolve complex tasks. Parent comment

Re:Introducing Agents in Haystack: Make LLMs resolve complex... by antti909 on Tuesday April 04, 2023 @06:12AM (#35437372)
That's also one of the ideas behind using so-called retrieval-based augmentation. You can 'plug' an LLM like OpenAI's one (of Cohere, or a combo) to your data and make it provide accurate answers, but still leveraging all the benefits and power or a cutting-edge generative model. Check this https://twitter.com/deepset_ai/status/1625495149446062081 or this https://twitter.com/deepset_ai/status/1621161534243368961
[ Parent | on HN ]
Re:Introducing Agents in Haystack: Make LLMs resolve complex... by irthomasthomas on Tuesday April 04, 2023 @09:27AM (#35439223)
This gives the model access to information, but it cannot eliminate the non-deterministic nature of the transformers model. There is always a non-zero probability that it will hallucinate.
[ Parent | on HN ]
Re:Introducing Agents in Haystack: Make LLMs resolve complex... by andrewljohnson on Tuesday April 04, 2023 @10:33AM (#35440279)
transformers are deterministic (if seeded).
[ Parent | on HN ]