Announcement
OpenAI says its Performance Factory puts Codex on ChatGPT slowdown duty
OpenAI says Codex agents investigate ChatGPT slowdowns, propose fixes for engineers to review, and check results.
TLDR
Codex doesn’t have to stay running while engineers review its fixes, OpenAI says. The company’s Performance Factory preserves task findings across agent and engineer handoffs, allowing work to resume when review feedback arrives. Alerts can start cloud investigations; after deployment, another agent checks whether performance has returned to baseline, the company says.
Combined views
7.1K
6 Sources, first seen ago

Comments