andre --dangerously-skip-permissions
@andrezfu • 1,519 subscribers
constantly learning!
Videos
Agents write application code, but you still get paged at 2am when it breaks. We wanted to know whether AI could handle that part of the job too. Introducing Incident Arena: a benchmark that puts coding agents on call! Check out our paper & full dataset release below!
andre --dangerously-skip-permissions56,351 views • 8 days ago
AI agents can't make transactions, which really bottlenecks their capabilities By giving them a secure embedded wallet, they're able to execute transactions with approval, and actually act autonomously! Are you ready for the world where your financial transactions are done on your behalf?
andre --dangerously-skip-permissions14,074 views • 1 year ago
No more content to load