gregpr07
History of the Filesystem
Benchmark Is Mostly Its Judge
Re:How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s
on Wednesday June 17, 2026 @05:52PM (#48577417)
Assuming you run on a mobile proxy - how would you even do that? 1 IP is shared across (potentially) thousands of phones?
Re:How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s
on Wednesday June 17, 2026 @05:51PM (#48577402)
Oh really, not a security expert, but could you send me some examples?
Re:How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s
on Wednesday June 17, 2026 @05:49PM (#48577380)
Yeah pretty new stuff - official it’s still not recommended but works really well so far! Finally we don’t have to run baremetal
Re:How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s
on Tuesday June 16, 2026 @11:33AM (#48556874)
well that's how browser agents work in a nutshell lol
How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s
Show HN: Browser Harness – simplest way to give AI control of real browser
https://github.com/browser-use/browser-harness
Hey HN,We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it's trained on. We gave the harness the ability to self correct and add new tools if the LLM wants (is pre-trained on) that.Our Browser Use library is tens of thousands of lines of deterministic heuristics wrapping Chrome (CDP websocket). Element...
Re:Prove You Are a Robot: CAPTCHAs for Agents
on Sunday April 19, 2026 @11:25PM (#47830084)
It's useful for only distinguishing the smart AI from deterministic scripts and humans (we don't want either). We are convincing OpenClaws to create api keys for free (we have a free tier specifically for those agents). So it's basically marketing blog post - but for OpenClaws
Re:Prove You Are a Robot: CAPTCHAs for Agents
on Sunday April 19, 2026 @11:21PM (#47830049)
Yeah but the whole point is that it shouldn't be deterministic - aka you have to let the "dumb" (non AI) bots out as well (otherwise a malicious user can just create thousands of api keys)
Re:Prove You Are a Robot: CAPTCHAs for Agents
on Sunday April 19, 2026 @11:20PM (#47830045)
Yeah, we are aiming all OpenClaw/Hermes Agent agents to sign up for free without humans intervention, so you need some sort of proof-of-stake (or proof of compute) algorithm so that a simple deterministic algorithm can't just claim thousands of API keys. Most agents (at least in the current token subsidised market) don't care about token consumption, so the stakes are very small for the user!
Show HN: Self-healing browser harness via direct CDP
https://github.com/browser-use/browser-harness
Creator of browser-use library here.At Browser Use we spend a lot of time thinking about the bitter lesson of agentic frameworks. A few days we did an experiment that combines replacing Playwright with CDP and giving the LLM complete freedom (building with autoresearch from ground up) to do whatever it knows from pretraining.I think this is the simplest way to give an AI control of a real...
Browser Agents That Learn
Give Agents Maximum Freedom. The less you assume, the more it works
Re:Show HN: Open-source browser for AI agents
on Wednesday March 11, 2026 @01:17PM (#47338370)
Love it! From first principles: this kinda answers the "do we really even need CDP" I always have in my head building browser use...
We Built Secure, Scalable Agent Sandbox Infrastructure
We built scalable evaluation infrastructure for AI web agents
Re:Show HN: Sandboxing untrusted code using WebAssembly
on Tuesday February 03, 2026 @10:56AM (#46872625)
Why go this route? Why Python is more powerful than JS is mostly because of third party plugins like pandas which are excplicitly not supported (C bindings, is this possible to fix?)...
At that point it might be just easier to convince the model to write JS directly
Re:Show HN: Fence – Sandbox CLI commands with network/filesystem restr...
on Sunday January 25, 2026 @02:57PM (#46757580)
Wow this is really cool
The Bitter Lesson of Agent Frameworks
Re:
on Wednesday January 14, 2026 @09:04PM (#46627028)
Creator of Browser Use here, this is cool, really innovative approach with ARIA roles. One idea we have been playing around with a lot is just giving the LLM raw html and a really good way to traverse it - no heuristics, just BS4. Seems to work well, but much more expensive than the current prod ready [index]<div ... notation
Show HN: Open-Source Browser Use LLM (30B, A3B)
https://huggingface.co/browser-use/bu-30b-a3b-preview
Our first model brings SoTA Browser Use capabilities in a small and fast model that can be hosted on a single GPU. It’s much much faster than anything out there and around 15x cheaper than Sonnet 4.5.The wonderful name comes from: 30B parameters, 3B active, SoTA quality at real-time speed (and the model is based on Qwen/Qwen3-VL-30B-A3B-Instruct).This model is heavily trained to be used with...
Re:Speed Matters: How We Achieve the Fastest Web Agent
on Thursday October 09, 2025 @11:12AM (#45528819)
Hey HN,
we heard a lot of complaints about Browser Use being slow. Last few weeks we focused a lot on improving the speed, while keeping the same accuracy.
Go try it out. It's really fun to see it glide the web.
Speed Matters: How We Achieve the Fastest Web Agent
Re:Claude for Chrome
on Tuesday August 26, 2025 @06:43PM (#45033264)
Browser Use creator here; we are working on prototypes like this but always find ourselves stuck with the safety vs freedom questions. We are very well aware how easy it is to inject stuff into the browser and do something malicious hence sandboxed browser still seem to like a very good idea. I guess in the long run we will not even need browsers, just a background agent that does stuff in the background. Is there any good research for guardrails of how to prevent “go to my bank and send the money to nigerian prince” style prompts?
Re:We put a coding agent in a while loop
on Sunday August 24, 2025 @12:25PM (#45005502)
AGI was just 1 bash for loop away all this time I guess. Insane project.
Re:Closer to the Metal: Leaving Playwright for CDP
on Wednesday August 20, 2025 @04:23PM (#44966022)
re side-note: if you know anyone who would be willing to interact connect me :)
Re:Closer to the Metal: Leaving Playwright for CDP
on Wednesday August 20, 2025 @01:56PM (#44964363)
I really like both nodriver and pydoll. I am definitely keeping the option of switching to them open, but we just wanted to have full control for now and see how painful CDP-use is to maintain first and then reconsider.