Top all-time · #5336
Browser Use Blog
Company blog · browser-use.com/postsaiprogramming
Browser Use Blog is the company blog at browser-use.com, writing about ai and programming. Since 2025, 14 different Hacker News readers have linked it 30 times, most often “Enable AI to control your browser”. It is still writing: the last post was on 2026-10-31, and you can follow it by feed.
Too few sampled comments (11) to say how often HN recommends it.?
Why HN links it
HN commenters link Browser Use Blog posts as references on browser agents: the SOTA technical report on evals, Playwright versus raw CDP harnesses, and sandboxing agents. The comments cite them without judging the writing.
Summarised by Claude from a sample of 11 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Browser Use is the cloud browser for AI agents. Run web agents that finish the task, or connect your own agent to stealth browsers at $0.02 an hour.
Most-linked posts?
- Enable AI to control your browser5 people · 5 mentions · first linked 2025-02-21
- /posts/sota-technical-report3 people · 4 mentions · first linked 2025-01-18
- The Bitter Lesson of Agent Harnesses3 people · 3 mentions · first linked 2026-04-24
- We Built Secure, Scalable Agent Sandbox Infrastructure2 people · 2 mentions · first linked 2026-02-27
What Hacker News says?
You could do that with browser-use: https://browser-use.com/
Comment linking /
on “Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code”Submitted Closer to the Metal: Leaving Playwright for CDP as a story · 182 points
HN discussionIt's not even SOTA. The actual SOTA is Browser Use (report here https://browser-use.com/posts/sota-technical-report )
Comment linking /posts/sota-technical-report
on “Operator research preview”Submitted The bitter lesson of browser agents as a story · 13 points
HN discussionYeah, and Browser Use already has 89% on WebVoyager https://browser-use.com/posts/sota-technical-report
Comment linking /posts/sota-technical-report
on “Operator research preview”Submitted How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s as a story · 3 points
HN discussionhave you looked at Browser Use? https://browser-use.com/
Comment linking /
on “Show HN: Superglue – open source API connector that writes its own code”Submitted Prove You Are a Robot: CAPTCHAs for Agents as a story · 3 points
HN discussionwhoops pasted the wrong link and it's too late to edit. meant to link to the updated article section here: https://browser-use.com/posts/playwright-to-cdp#:~:text=Sele...
Comment linking /posts/playwright-to-cdp
on “Closer to the Metal: Leaving Playwright for CDP”Submitted A stealth benchmark of major cloud browser providers as a story · 3 points
HN discussionAnyone compare this with BrowserUse ? https://browser-use.com/
Comment linking /
on “Playwright Tools for MCP”Submitted Browser agent bot detection is about to change as a story · 2 points
HN discussionWe started with using browser-use because they had the best evals: https://browser-use.com/posts/sota-technical-report - but we found that Laminar came out with a better browser agent (& a better eval): https://www.lmnr.ai/ so we're looking to migrate over soon!
Comment linking /posts/sota-technical-report
on “Show HN: Web-eval-agent – Let the coding agent debug itself”Submitted Show HN: An Open-Source Benchmark for AI Browser Agent Models as a story · 2 points
HN discussionYes, this is the report of browser-use with 89%: https://browser-use.com/posts/sota-technical-report We definitely need a new dataset with more complex tasks, like uploading files, handling multiple tabs, and handling many more steps.
Comment linking /posts/sota-technical-report
on “Skyvern Browser Agent 2.0: How We Reached State of the Art in Evals”Submitted The Bitter Lesson of Agent Frameworks as a story · 2 points
HN discussionCheck the post from Simon Willison: https://til.simonwillison.net/claude-code/playwright-mcp-cla... You install the playwright mcp server and then it just launches chrome. Also check out https://browser-use.com/ https://github.com/browser-use/browser-use and https://github.com/D4Vinci/Scrapling
Comment linking /
on “Agentic Coding Slot Machines – Did We Just Summon a Genie Addiction? – Part 1”Submitted Benchmark Is Mostly Its Judge as a story · 1 points
HN discussionOne blog post how we built agent sandbox infrastructure with unikraft - we still use unikraft for agent sandboxes and love the technology. https://browser-use.com/posts/two-ways-to-sandbox-agents
Comment linking /posts/two-ways-to-sandbox-agents
on “How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s”Submitted The Bitter Lesson of Agent Harnesses as a story · 1 points
HN discussion> Browser stealth has been a solved problem for some time now That's not true. Bots can still automate the web and there's demand for products that allow it. It's harder than years ago, but not impossible. Defenders are always in favor, but the demand for automating the web exists, so research keeps going. There are ways to hide everything, including residential proxies. For reference, I'm the blog author, and I hav…
Comment linking /posts/bot-detection
on “How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s”Submitted Browser Agents That Learn as a story · 1 points
HN discussionagent-browser uses playwright so it struggles with things like cross-origin-iframes - on the other hand, browser harness uses raw cdp, which is unrestrictive. It's discussed in this blog post! https://browser-use.com/posts/bitter-lesson-agent-harnesses
Comment linking /posts/bitter-lesson-agent-harnesses
on “Show HN: Browser Harness – simplest way to give AI control of real browser”Submitted How Auto-Research built the SOTA browser agent as a story · 1 points
HN discussionWhat do you think about this? https://browser-use.com/posts/bitter-lesson-agent-harnesses
Comment linking /posts/bitter-lesson-agent-harnesses
on “Show HN: A REPL for browsers that agents love”Submitted Give Agents Maximum Freedom. The less you assume, the more it works as a story · 1 points
HN discussionSubmitted We Built Secure, Scalable Agent Sandbox Infrastructure as a story · 1 points
HN discussionSubmitted We built scalable evaluation infrastructure for AI web agents as a story · 1 points
HN discussionSubmitted Speed Matters: How We Achieve the Fastest Web Agent as a story · 1 points
HN discussionSubmitted Enable AI to control your browser as a story · 1 points
HN discussion