# "How good are slop-vestigators?" by Hasan Baig, OscarGilg, Hamzah

Page: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah
Text version: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah.md
Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401)
Published: 2026-09-09T19:58:21+00:00
Episode link: https://www.buzzsprout.com/2037297/episodes/19781284-how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah.mp3
Audio file: https://www.buzzsprout.com/2037297/episodes/19781284-how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah
Duration seconds: 824

## Resource

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 under our rubric and that model performance improves with time budget and general capability.We observe OpenAI models are less likely than other models to suggest the incident came from an interna...

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/how-good-are-slop-vestigators-by-hasan-baig-oscargilg-hamzah.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.