Earlier quoted context omitted.
Would be really cool if you could tie this into Claude's computer use APIs!
My wallet just ran way. Come back you!
Haha with browser use or Computer use??
Show HN: I wrote an open-source browser alternative for Computer Use for any LLM
71–75 of 75 posts
Re: Show HN: I wrote an open-source browser alternative for Computer Use for any LLM
#72Is it decided then that screenshots are better input for LLMs than HTML, or is that still an active area of investigation? I see that y'all elected for a mostly screenshot-based approach here, wondering if that was based on evidence or just a working theory.
[dead]
Tried Agent-E, like the DOM distillation to reduce token method. I've started using AgentQL for a new project, which works well combining playwright.
Re: Show HN: I wrote an open-source browser alternative for Computer Use for any LLM
#73Many web developers use Playwright and Puppeteer, so why Selenium?
Re: Show HN: I wrote an open-source browser alternative for Computer Use for any LLM
#74Re: Show HN: I wrote an open-source browser alternative for Computer Use for any LLM
#75It's impressive, but to me it seems like the saddest development experience... agent = Agent( task='Go to hackernews on show hn and give me top 10 post titels, their points and hours. Calculate for each the ratio of points per hour.', llm=ChatOpenAI(model='gpt-4o'), ) await agent.run() Passing prompts to a LLM agent... waiting for the black box to run and do something...
I mean, is that really much different than an API? I pass a query, and get data back, and rarely do I get to inspect the mechanisms behind what's returning that data.
It may give more transparency if it output the code to do scrapping with playwright.
Then we can review the code before actually running it.
And the reviewed result can be saved for future running.