Pinned
We're now @ApolloResearch.
Same team, same mission. A better handle that reflects that research is at the core of everything we do.
If you've been following us as @ApolloEvals, nothing has changed.
Apollo Research
@ApolloResearch
Our goal is to secure frontier AI systems from development, to deployment and governance.
- We hosted a webinar with @Tailscale on safely scaling AI coding agents. We cover how Aperture + Watcher provide visibility, runtime controls and behavioural monitoring, with a demo of Watcher blocking data exfiltration after a prompt injection. Video:
- Apollo Research ran its first external red-teaming campaign for Anthropic’s auto mode. Now auto mode is the default permissions mode in Claude Code. After hardening based on Apollo’s findings, the classifier's miss rate fell from 12% to 7%. 🧵
- New episode with @MLStreetTalk: our research team does a deep dive on reward-seeking in AI models. The Episode covers our recent paper with OpenAI and what these findings mean for how we evaluate frontier systems. Filmed a week before the OpenAI/Hugging Face incident, which
- What makes a good prompt for monitoring? We find that 1. providing a reasoning structure for the model is by far the most important component, followed by 2. severity rubric and 3. worked examples Everything else barely matters (in our setting).
