papers-please

Is there a credible solution to the LLM hallucination problem?

Any interesting research papers or discussions on this?

Technowatermelon. Elder Millenial. Building Farcaster. 

nf.td/varun

How prevalent is it in coding applications? Feels like I never experience LLM hallucination but coding is pretty much my only use case

I get a lot of hallucinations for Solidity specifically, and a the odd hallucination with newer libraries

Like, this isn’t how this works at all. Cursor IDE

Engineer on Base 🔵 • Building BlockSocks 🧦 • Denver, CO 📍

I have triaged ChatGPT bug reports on Immunefi for SQL injections in the middle of solidity smart contracts 😄

I do really like auditing code with Cursor though, being able to feed the entire codebase into the context window and ask questions is super useful. It's like working with a hyper observant five year old.

Actually you’re right, I also experience this. I think I’ve got a pretty decent idea of what the AI probably wouldn’t be good at these days which I just avoid asking it about in the first place. Recency bias in my original reply