Jonathon's AI Wiki

Tag: anthropic-research

2 items with this tag.

  • May 22, 2026

    The Capability Curve — Jeremy (Anthropic Research PM)

    • code-with-claude-london
    • coding-capabilities
    • anthropic-research
    • swe-bench
    • long-horizon-agents
    • evals
    • scaffolding
    • auto-mode
    • claude-code
    • capability-curve
  • May 08, 2026

    Translating Claude's Thoughts Into Language — Activation-to-Text Interpretability

    • interpretability
    • mechanistic-interpretability
    • activations
    • alignment
    • safety-evals
    • anthropic-research
    • blackmail-test
    • self-introspection
    • claude-mythos-preview

Created with Quartz v4.5.2 © 2026

  • ✦ Explore the graph in 3D