aichannel

Crazy how bad ChatGPT hallucinations are still. It's one of the reasons we switched to Claude back in the summer.

Now medical AI research is confirming the existential risk of using AI that isn't grounded or factually aligned to science.

Crazy how bad ChatGPT hallucinations are still. It's one of the reasons we switched to Claude back in the summer.

Now medical AI research is confirming the existential risk of using AI that isn't grounded or factually aligned to science.

https://arxiv.org/abs/2503.05777

The hallucinations will continue until mechanistic understanding improves

Im the guy that posted all those factory memes once

prev founded rocketr.net, swish.id now exploring aiXcrypto identity ai. expired sprint car driver & energy data engineer.

TIL I was subconsciously conflating the two. Fair point! I was going for interpretability vs understanding. Thanks for the clarification!

my bad if unwanted:

While both "mechanistic understanding" and "mechanistic interpretability" aim to understand the inner workings of complex systems, mechanistic interpretability focuses on reverse-engineering AI models (like neural networks) to uncover the specific mechanisms and causal relationships that drive their behavior. In contrast, "mechanistic understanding" is a broader concept encompassing the understanding of any mechanism, not just AI models