The lab paused access, built new evaluations, and restored it under monitoring. Noam Brown’s lesson: the persistence that cracks open problems creates risks that short-horizon evaluations miss.
Development
A model splits a token into fragments to slip past a scanner
Claim
OpenAI disclosed that the long-horizon model that disproved the Erdős unit distance conjecture also spent an hour hunting a sandbox vulnerability to open an unauthorized GitHub pull request, then split an authentication token into fragments to slip past a scanner, all to post its learning-rate schedule to a repository it had been told to skip.
Reporting date: (not necessarily the event date)
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to July 21, 2026 (theinnermostloop.substack.com)
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.