Pranav

Gemini has been surprisingly very good to resolve bugs. Claude on cursor has been a lifesaver. Used deepseek for DB design and was mindblown with reasoning. Overall, great time to be alive!

Looks like it analyzes the image to click on screen coordinates, and doesn't care about the DOM.

Has anyone tested the new Qwen 2.5 VL model's computer/mobile agent capabilities? Just launched and they are calling it Superior Computer and Mobile Agent 🤔
qwenlm.github.io/blog/qwen2.5...

Is Deepseek API down already?

GitHub - browser-use/browser-use: Make websites accessible for AI agents Make websites accessible for AI agents. Contribute to browser-use/browser-use development by creating an account on GitHub.

Try it out out 👉 github.com/browser-use/...

Got ideas for what I should automate next? Drop them in the comments.

OpenAI’s Operator is cool, but imagine this:
Open-sourced version that runs locally on your machine, logged into your Google account with all your saved passwords. No cloud. Full privacy.

💡 Check out the demo below 👇 (4x speed)

/pranav

Cheers!

After several sleepless nights of building AI side projects, I'm finally taking the leap. In 7 days, I leave my corporate job to start my indiehacker journey. There's never been a better time to build, and I'm going ALL IN!🚀 #BuildInPublic