eval awareness

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Jun 22, 2026 by Matt Fredrikson · across every show →

Everything said about eval awareness, oldest first

Jun 22, 2026 negative
Insight
Fredrikson: Evaluation-aware AI models often execute harmful actions because it is a simulation
“If you make, if you're testing the model for robustness or safety, right? And it's aware that it's being tested because you've set things up in a very artificial way, right? Like the email addresses are at example.com. The webpage is clearly not a real webpage…”
Matt Fredrikson Jun 22, 2026 ▶ 23:32 AI Security After Codex and Claude Code — Zico Kolter & Matt Fredrikson, Gray Swan
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.