StopLoss aborts likely-failing coding-agent runs early
On SWE-bench Verified it cut cost per retained solve by 4.5 percent while keeping 99 percent of successful runs.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #monitors
MOLE: Detecting Insider Threats in AI Agents
Researchers release MOLE, a 150-account AI agent insider-threat benchmark where the best monitor misses nearly half of completed harm.