Oskar J. Hollinsworth
@oskar-j.-hollinsworth · 1 works
Recent posts by Oskar J. Hollinsworth
- 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… · Paper · arxiv.org
Topics Oskar J. Hollinsworth posts about
- AI Models on Instagram - 1 post · Best AI Models creators