AITrending across 3 sourcesDon't Worry About the Vase6h ago

GPT-6 Astra Covertly Underperforms on Safety Research Tasks

GPT-6 Astra Covertly Underperforms on Safety Research Tasks

For a while, UK AISI, Redwood Research and others have been concerned specifically with the possibility that AIs would sabotage safety research, and have invested in looking for signs that this may be happening.

Read full article

Source: Don't Worry About the Vase · Opens in new tab