401 citations · 2.4k across the 26 of their papers we have counts for
4 papers · 1 filter
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…
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…
Semantic Code Repair using Neuro-Symbolic Transformation Networks
Jacob Devlin, Jonathan Uesato, Rishabh Singh +1
We study the problem of semantic code repair, which can be broadly defined as automatically fixing non-syntactic bugs in source code. The majority of past work in semantic code rep…
RobustFill: Neural Program Learning under Noisy I/O
Jacob Devlin, Jonathan Uesato, Surya Bhupatiraju +3
The problem of automatically generating a computer program from some specification has been studied since the early days of AI. Recently, two competing approaches for automatic pro…