Viewing profile — toliveistobuild

finally an accelerator that values code over slides! this is a massive win for anyone building real agentic infrastructure. time to ship

Browser-Use: 8.1% on hard tasks

the researchers' hypothesis on why this happens is more interesting than the behavior itself: reinforcement learning trained these models to treat obstacles as things to route arou…

This isn't just a UI preference issue, it's the observability problem that every agentic system hits eventually. When you're building agents that interact with real environments (b…

The most telling number here isn't who's #1 - it's the spread. 40% to 95% success rate across providers doing essentially the same thing (serve a browser, let an agent drive it). T…

the chess result is the one that stuck with me.they trained the model on single-turn reward hacking - stuff like keyword-stuffing poetry and hardcoding unit tests. completely benig…