Anthropic released a deeper paper on the agentic misalignment.
- Anthropic released a deeper paper on the agentic misalignment.
- That is, how the model would choose to blackmail its creators in some cases.
- Simon Willison's summary is worth reading.
From other episodes
- This week in the Wild West Roundup:2026-04-20
- Simon Willison: "Shocking result on my pelican benchmark this morning, I got a better pelican from a 21GB local Qwen3.6-35B-A3B running on my laptop than I did from the new Opus 4.7!"2026-04-20
- What percentage of Claude Code usage produces code that is basically the same as what another user distilled?2026-04-13
- How much of Anthropic's crazy revenue growth is Meta employees?2026-04-13
- Consumer AI is being absorbed.2026-03-30
- A friend who conducts multiple agent swarms recently had his Claude Max account turned off by Anthropic.2026-03-30
- It's pretty clear the major labs are moving away from "all you can eat" subscription pricing for models.2026-03-23
- Dean Ball has an excellent analysis on the far-reaching negative implications of the Pentagon's labeling of Anthropic as a supply chain threat.2026-03-17