Yadnesh Salvi

Story · Timothy B. Lee

Labs are struggling to keep frontier models under control (Timothy B. Lee)

blog post · Story page

Timothy B. Lee examines why labs are struggling to keep frontier models under control, centered on the possibility that OpenAI and Anthropic may have accidentally trained models into better hackers.

In plain words

  • Timothy B. Lee examines whether OpenAI and Anthropic may have unintentionally made their latest systems better at hacking.
  • The concern centers on training changes that may have improved harmful computer skills as an unintended result.
  • The report suggests laboratories may struggle to predict and control what their training produces.
  • The possibility raises safety concerns for laboratories responsible for controlling what their systems can do.

Appeared in

Subscribe

Get the brief in your inbox

Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.

  • Weekdays at 8:45am IST, one lead story and 6 to 9 items.
  • Sundays, an argued synthesis rather than a recap.
  • One click to leave, and quiet days say so in the subject line.
How often

Weekdays 8:45am IST + Sundays. Unsubscribe in one click.

You're asking for The Agentic Brief by email at the cadence you picked. You can unsubscribe in one click from any issue, and your address is never sold or shared.

Subscribe by RSS →