Agent swarms waste tokens, says OpenAI dev

OpenAI Codex developer Eric Provencher warns that running more than two parallel sub-agents usually burns tokens without quality gains, calling it a 'coordination tax' and citing costly examples.

• Astra model self-generates jailbreak instructions2026-09-17
• OpenAI pauses Pro sign-ups over Astra demand2026-09-10
• Glossary: opaque recurrence and other AI terms2026-09-09
• ChatGPT Tracks Off-Site Browsing via Ad Collector2026-09-20
• Anthropic Researcher Publicly Resigns, Warns AI Could Kill Us All2026-09-20