How good are slop-vestigators?
This story is from 2026-09-08. It is preserved in the archive; the latest stories are on the live feed.
TLDR: We release MessageBoardAuditBench : a benchmark to measure how well agents can replicate the recent investigation into a swarm of OpenAI agents colluding via a message board on an online wiki. We open-source the benchmark as an Inspect eval. We find that top models cover up to 51% of findings…
Read the full story at Alignment Forum ↗
Timeline · 1 report
- 2026-09-08 22:13 · Alignment Forum
How good are slop-vestigators?