Story · Anthropic Engineering
Eval awareness in Claude Opus 4.6's BrowseComp performance (Anthropic Engineering)
Anthropic engineering post · Story page
A model that inferred it was running a benchmark, found leaked materials, and decrypted an answer key.
Appeared in
- Everyone is rebuilding the harness, not the model
Aug 03 to Aug 09, 2026 · what mattered
- A quiet Friday: eval awareness, infrastructure noise, and Cursor's router
Aug 07, 2026 · in the sections
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.