2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The red-teaming methodology and highlighting new attack vectors aim to help defenders evaluate their mitigations against the possibility of persistent malign coding agents and prevent multi-context attacks at an acceptable cost.
Overthinking is introduced, the process of using reasoning task vectors to amplify the propensity to think out loud of reasoning models, and reasoning amplification may surface secrets or unintended behaviors acquired during training up to $10\times$ more frequently than the original reasoning model.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
