activity
20202026
most citedScaling Language Models: Methods, Analysis & Insights from Training Gopher

243 citations · 364 across the 9 of their papers we have counts for

collaborators

11 papers

cs.CR2026

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

Hoagy Cunningham, Jerry Wei, Zihan Wang +26

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to prev…

cs.AI2025

Natural Emergent Misalignment from Reward Hacking in Production RL

Monte MacDiarmid, Benjamin Wright, Jonathan Uesato +19

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, im…

cs.AI2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…

cs.CL20259 cited

Reasoning Models Don't Always Say What They Think

Yanda Chen, Joe Benton, Ansh Radhakrishnan +12

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effecti…

cs.AI20251 cited

An Approach to Technical AGI Safety and Security

Rohin Shah, Alex Irpan, Alexander Matt Turner +27

Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough…

cs.CL202254 cited

Teaching language models to support answers with verified quotes

Jacob Menick, Maja Trebacz, Vladimir Mikulik +8

Recent large language models often answer factual questions correctly. But users can't trust any given claim a model makes without fact-checking, because language models can halluc…