[r-zip]

Deep nets are notoriously overconfident in their predictions. So why do you expect this approach to succeed?

[cl42]

The broader package I’m working on (PhaseLLM) is specifically focused on devtools for observability and robustness of LLM-powered products. I agree with you that there are lots issues with LLMs and taking them to production. I’m hoping products like this + making them robust will help improve the research as well as the UX.

[nullsense]

>Deep nets are notoriously overconfident in their predictions

Sounds a lot like humans