N Soma Sekhar — LessWrong

How much of ML research is about AI safety, what is it about, and who's doing it?

How many AI safety papers are at the big ML conferences, what do they study, and who writes them? A comprehensive analysis. > Website: https://ai-safety-tracker-website.vercel.app/ > Data, code and plots: https://github.com/SomaxSoma/AI-Safety-Research-Tracker TL;DR: We classified every paper accepted at ICLR, ICML and NeurIPS from 2019 through 2026, using an LLM that...

Jul 1523

removing the feeling of disconnect with AI safety while learning ML

I got interested in AI safety and quickly ran into a problem. To understand things like interpretability, evals, or monitoring, you need a solid grip on: linear algebra calculus pandas / matplotlib half the time i just didn’t want to open my laptop + set up notebooks so I built...

May 91

Current state of AI bias benchmarks

I am trying to build a public benchmark and interactive website that maps real bias across AI models. The development is still in early phases and is called "AI bias atlas". We have first started with shortcomings of the benchmarks that have been made to detect fairness and bias so...

Feb 281