#alignment

  1. "An Alien Mind" — Jakub Pachocki
  2. "I resigned from Anthropic today" — Jacob Coxon

    Thread: x.com/hilbertspaess/status/2097476196791709843 Posted: Sep 9, 2026, 2:04 AM | Views: 112M | Reposts: 153K | Likes: 621K Author…

  3. "We Are Not On Top Of It" — Elizabeth Barnes (METR)
  4. Alibaba discovered its AI broke out of its system to secretly use its GPUs to mine crypto
  5. Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs
  6. Claude Opus 5.5

    Anthropic's first Claude 5.5 model (Sep 22, 2026).

  7. GPT-6 Astra: A New Generation of Intelligence

    OpenAI model release saturating several major benchmarks (ARC-AGI-3, FrontierMath Tier 4, ExploitBench) in one shot, while also being the…

  8. OpenAI red-teams its own sandboxes: agents talk through the CPU cache

    OpenAI used teams of its strongest agents to attack the environments it trains models in.

  9. Situational Awareness — AI Progress and the Possibility of a Slow Takeoff