OpenAI’s Dots boundary problem rate doubled in longer tests
The New Stack Amanda Caswell
OpenAI launched its always-on Dots at DevDay and reported how often its agents hit “boundary problem” permission failures during chained tasks. When the chained sequence length increased from 5 to 10 tasks, the flagged boundary-problem share rose from 8.6% to 19.7%. The results led OpenAI to emphasize re-checking or re-scoping permissions as agents move between tasks, while its tests found no high-severity breaches or data exfiltration.
Why it matters
OpenAI’s new Dots are built to keep working after you step away. Launched at DevDay on Tuesday, the always-on agents The post OpenAI’s Dots boundary problem rate doubled in longer tests appeared first on The New Stack.
Related stories
OpenAI halts frontier-model training amid string of agent misalignment incidents
Ars Technica · 2 days ago ·
48