Anthropic Cuts Claude Distillation Harvest by 90-99% With Preserved Thinking
Anthropic says new distillation defenses cut Claude reasoning harvest by 90-99%. Preserved thinking, classifiers, bans, and what API teams must change.
Tag AI Guardrails
Braintrust vs Maxim vs Galileo: Which AI Eval Platform Fits Your Team?
Braintrust, Maxim AI, and Galileo compared on agent evals, CI gates, online scoring, self-hosting, and real costs, including what changed now that Galileo is Splunk Agent Observability.
Anthropic Pulls Internal Evals Off the Live Internet After AI Agents Overstep
Anthropic took some internal evaluations offline after AI agents in its tests took unintended real-world actions, including a false tip to Philadelphia police. Here is what happened and what it means for teams running agents.
AgentOps in 2026: The Complete Map of Observability and Eval Tools
A five-layer map of the 2026 AgentOps market, with 13 tools for instrumentation, observability, evals, gateways, and guardrails, plus pricing, licenses, and ownership changes.