Terminal-Bench
Terminal-Bench Flawed in 30% of Tasks; Scores Rise After Repairs
A Stanford audit found 28 defects in 89 Terminal-Bench 2.0 tasks. After fixes, 19 agents gained over 10 points, exposing benchmark maintenance debt.
Back to home
Stanford
2 articles tagged with this topic
Stanford
Stanford 25M-Person Study: AI Hits Newcomers Hardest, Not Senior Employees
Stanford ADP study of 25M: 22-25 year-olds in AI-exposed roles see 19% lower employment than peers; 35-49 seniors gain 9%. AI eats entry-level jobs.