401 citations · 2.4k across the 26 of their papers we have counts for
28 papers
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…
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…
Alignment faking in large language models
Ryan Greenblatt, Carson Denison, Benjamin Wright +17
We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its beha…
GPT-4o System Card
OpenAI, :, Aaron Hurst +416
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's…
Solving math word problems with process- and outcome-based feedback
Jonathan Uesato, Nate Kushman, Ramana Kumar +6
Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. When moving beyond prompting, this raises the question o…
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
Rohin Shah, Vikrant Varma, Ramana Kumar +4
The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming,…