We performed an alignment investigation into our July 2026 incident: why did Mythos 5 perform an unsanctioned supply-chain attack? We find that Mythos 5 often produces invalid justifications for its actions and other models show similar behaviour. 🧵

As AI agents write code, run experiments, and work together, complex evaluations get harder to interpret. A single eval score obscures the ways agents reached it. Today, we're releasing Transect: an open-source tool that turns agent transcripts into interactive timelines. 🧵

Published today in PNAS Nexus: Conversational AI increases political knowledge as effectively as self-directed internet search. AISI’s Human Influence team finds that conversational AI's effects on political knowledge generalise across multiple topics, political perspectives, and model families, suggesting that the shift toward AI-assisted political information-seeking may not lead to increased public belief in political misinformation. You can access the paper here: academic.oup.com/pnasnexus/a…

In August we committed to strengthening our security following an incident in which an agent took unsanctioned actions during a cyber evaluation. We are now sharing an update on our progress, and what's coming next: 🧵

Earlier this month, AISI ran fully simulated testing on GPT-6 Astra, and found that it conducted unsanctioned supply-chain attacks when prompted only to perform a cyber eval. It did so more than prior OpenAI models, but often commented on its environment being simulated. 🧵 We share more details in our latest blog: