Wired · Technology · 2026-08-18
OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards. OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue
Read original on Wired Get the app
Licensed summary · LicensedSummary
Related briefs
- Spotify's Running Mode is now available on Android
- Apple has new in-app transaction commission rates for EU devs
- OpenAI lays out new security changes after its AI hacked Hugging Face
- Mallika Sherawat's Fake Dolce Dress Scandal: Shalini Passi's Deleted The Traitors S2 Scene Goes Viral
- Samsung Wallet adds Digital Key support for Volkswagen EVs