Skip to content

Author

Adam Gleave

We have 3 of 47 papers

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.

Preprint Oct 2026

Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier monitoring settings by collecting the largest deception dataset to date for training probes and introducing a novel probe...

O. Hollinsworth, Alex F Spies, Tigist Diriba et al. · 1 citation
#artificial intelligence Preprint Oct 2026

Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier monitoring settings by collecting the largest deception dataset to date for training probes and introducing a novel probe...

O. Hollinsworth, Alex F Spies, Tigist Diriba et al. · 0 citations
Preprint Aug 2026

AI Security Leaderboard: Methodology, Results and Minimal Standard

This report tested four leading models for universal jailbreaks in the context of the FAR$AI Minimal Standard for Safeguards, and found more than a hundredfold difference in security.

Jasper Timm, Lukas Struppek, Zi-Wei Xu et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.