Professor uses Codex to audit papers' replication data, finds serious errors everywhere
RexDouglass · x · 2026-10-15
A professor shares that during tenure/promotion letter season, he has Codex automatically pull replication data whenever he reads a paper. The tool keeps surfacing serious mistakes in researchers' code and data — including his own papers. "We are in for it," he warns, hinting that AI-assisted replication audits could expose widespread reproducibility problems in academia.
More from coding & agent
- Open-Agent-Email: free open-source alternative to AgentMail for AI agents — matchaman11 · 2026-10-15
- AWS Gen AI Weekly Redesign: One-Page Exec Summary, AgentCore Memory Goes Usage-Based — DigitalColmer · 2026-10-15
- Nous Research Launches 50+ Connectors for Hermes Agent, No Account Required — NousResearch · 2026-10-15
- Dev group chat: skip runtime LLM web search, index products via API instead — vxnuaj · 2026-10-15
- Tev-Gym: 1,170 dense-reward RL environments push long-horizon agentic training — RulinShao · 2026-10-15
- Microsoft's AutoEnvScaling lets agents build their own RL environments, lifting Qwen3 Terminal-Bench from 41.1 to 53.3 — omarsar0 · 2026-10-15