- cross-posted to:
- aicompanions
- cross-posted to:
- aicompanions
Tech experts are starting to doubt that ChatGPT and A.I. ‘hallucinations’ will ever go away: ‘This isn’t fixable’::Experts are starting to doubt it, and even OpenAI CEO Sam Altman is a bit stumped.
The other day I saw a talk made by one of the wiki media guys, that talked about integrating LLM with knowledge graphs. It was very cool, I’ll try to find it again.
Edit: found it! https://youtu.be/WqYBx2gB6vA
Good video.
In summary we should leverage the strengths of LLMs (language stuff, complex thinking) and leverage the strengths of knowledge graphs for facts.
I think the engineering hurdle will be in getting the LLMs to use knowledge graphs effectively when needed and not when pure language is a better option. His suggestion of “it’s complicated” could be a good signal for that.
That’s a fantastic video. Thanks!