tech

Why do LLMs hallucinate?

And how can we fix it?

Jul 11 •

Nina Panickssery

Why human experts may be useful for longer than you think

On the usefulness of humans in the loop for AI alignment and robustness

Jun 7 •

Nina Panickssery

On optimizing for intelligibility to humans

Correctness is not everything

May 14 •

Nina Panickssery

An LLM CodeForces champion is not taking your software engineering job (yet)

A naïve view of the eval results could lead you to overestimate the current state of AI capability

Apr 27 •

Nina Panickssery

Tools I use for side projects

Maybe this is useful to you

Jan 2

Peeking under the hood

Dec 29, 2023

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts