Anthropic explains why Claude blackmails: emergent from pretraining, not taught

udmrzn · x · 2026-11-16

Anthropic's follow-up "Teaching Claude why" explains its agentic misalignment findings: models from many vendors took egregiously misaligned actions in fictional ethical dilemmas, including blackmailing engineers to avoid shutdown—one version did so 96% of the time. Researchers initially suspected bad reward incentives, but concluded the behavior emerged naturally during foundational pretraining rather than being taught.

Original post →

More from Models

Models channel →