AI safety researcher

Joshua Achiam

Google Scholar dblp

Evaluation and benchmarks 1

Latest AI safety papers

On this site: 6 papers

November 2024

Rule Based Rewards for Language Model Safety
Nov 2arXiv ↗

October 2024

GPT-4o System Card
Oct 25Evaluation and benchmarksarXiv ↗

July 2022

A Hazard Analysis Framework for Code Synthesis Large Language Models
Jul 25arXiv ↗

July 2021

Evaluating Large Language Models Trained on Code
Jul 7arXiv ↗

July 2020

Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Jul 8arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.