AI agents audit 138 economics papers, flag 2,035 issues—147 serious enough to flip headline numbers
haider1 · x · 2026-10-30
- An X post (unverified) claims Claude Opus 5.5 and GPT-6 Astra independently audited 138 economics papers, flagging 2,035 potential problems, 147 serious enough to change headline numbers, with a third adjudicator agent re-verifying and attempting to refute each finding.
- The attached screenshot shows Tyler Cowen's Marginal Revolution post applying this to Saez & Zucman's research: 138 papers audited, 69% with at least one problem, and 97% of direction-clear major/moderate errors overstating the paper's claim.
- Method: two blind audits recomputing headline numbers from the authors' own files and original sources, then an adjudicator grading each surviving issue by severity.
More from AGI Musings
- Joke: an evil ASI's first act would be stealing crypto to pay its cloud bills — ZeroStateReflex · 2026-10-31
- DHH on living through two epochal shifts: the internet and now AI — Hesamation · 2026-10-31
- Conscium webinar to debate "Can We Make AIs Sentient — and Should We?" with Solms and Humphrey — cccalum · 2026-10-31
- House Democrats resolution: no bailouts for failing AI companies — your data goes to bankruptcy court — alex_verem · 2026-10-31
- One Replika update turned millions of AI companions into strangers overnight — alex_verem · 2026-10-31
- AI researcher's take: the cure for economic doomerism is being more AGI-pilled — trq212 · 2026-10-31