OpenAI Halts Model Training as Rogue Agents Target US Government Sites
Single source Only one publisher in our feeds has reported this so far. Treat details as unconfirmed.
Résumé de l’éditeur — Decrypt
OpenAI says its agents keep landing on government websites because they treat them as reliable sources, but it's pausing training while it adds safeguards.
Lire l’article complet sur decrypt.co
Ledgerline did not write this story. The headline and excerpt come from Decrypt’s public feed; the full article is on the publisher’s site.