Chen Li

We have a major release coming up

I just tried a browser tool from Fellou, and it works. 2025 is a big year for browser and web agent.

I'm using the Fellou AI browser to publish this post.

@ajay_sreeram @TsingYoga We just released a new desktop version with UI-TARS-1.5 support: github.com/bytedance/UI-T…

@TsingYoga I was trying 1.5 7b, it always tries to click few pixels above diagonally. Do we need to pass screen size somewhere from desktop app?

Introducing UI-TARS-1.5, a vision-language model that beats OpenAI Operator and Claude 3.7 on GUI Agent and Game Agent tasks. We've open-sourced a small-size version model for research purposes, more details can be found in our blog. TARS learns solely from a screen, but generalizes beyond a screen! Blog: seed-tars.com/1.5 Model: github.com/bytedance/UI-T… App: github.com/bytedance/UI-T…

@billyuchenlin quite difficult

😅Math Olympiad becomes easier for AI; Common sense is still hard.

@henryyorkbb Monica AI is awesome