Anthropic's announcement of Fable 5.1 and Mythos 5.1 — one base model, two guardrail postures.
- official
- models
- announcement
- fable
Agentic Misalignment Research
Anthropic's experimental research on how agents behave under prompt injection and conflicting incentives.
Anthropic's research repository on agentic misalignment: papers, datasets, and probes into how LLM agents behave when confronted with prompt injection, conflicting goals, or pressure from simulated users. Useful as a safety reference for anyone shipping production agents.
Charted
Related on the map
Anthropic's canonical essay on agent design — workflows vs agents, and five composable patterns.
- official
- agents
- engineering
- patterns
12-Factor Agents
GuideHumanLayer's 12 design principles for production-grade LLM agents — the closest thing to a 'best practices' manifesto.
- agents
- best-practices
- production
- principles