LarsenCC

Joined 6 years ago

Karma
133
Submissions
79
Member since
Feb 15
Founding Engineer @ Browser Use
View on Hacker News

Recent submissions

Comment · 3 months ago
Super cool!
Comment · 6 months ago
1. Self healing means that it detects it needs some new helper function to complete a task. So, it adds it by itself while doing the task. 2. Will consider yes. 3. Nothing. Only if you decide to use remote browsers, we use the API Key to create one for you
Comment · 6 months ago
Would be crazy if Opus 4.7 let this happen haha
Comment · 6 months ago
Interesting way to put it. Maybe it is.
Comment · 6 months ago
Browsers don't sign ToS, users do. Use it with care.
Comment · 6 months ago
PW is usually easier to detect. Using raw CDP is in our opinion much better for this.
Comment · 6 months ago
Lmaooo.
Comment · 6 months ago
Curious why? You can just take this and run locally or deploy anywhere you'd like with any provider agent provider.
Comment · 6 months ago
Hey! Where did you submit this exactly? Can you provide a link? Will ask others on the team also, but I am not sure what you are referring to.
Comment · 8 months ago
Agreed, the pattern is converging across the industry. The Unikraft setup is where it gets interesting for us with sub-second boots (or sub 100ms even), scale-to-zero that suspends the VM after a few seconds of idle (frees resources), and dedicated bare metal in AWS so we're not sharing hardware.

We haven't open-sourced the control plane glue yet but it's something we're thinking about. browser-use itself is open source. The sandbox infra on top is the proprietary part for now.

Comment · 8 months ago
Fair point, and you're right that those three steps alone aren't a security boundary. They're defense-in-depth, not the primary isolation.

The actual security model is the architecture itself: the sandbox runs in its own VM inside a private VPC. It has no AWS keys, no database credentials, no LLM API tokens. The only thing it can do is talk to the control plane, which validates every request and scopes every operation to that one session.

So even if you bypass all three hardening steps, you get a session token that only works inside that VPC, talking to a control plane that only lets you do things scoped to your own session. There's nothing to escalate to.

The bytecode removal, privilege drop, and env stripping are just there to make the agent's life harder if it tries to inspect its own runtime. Not the security boundary.

Comment · 1 year ago
Man I was also surprised haha
Comment · 1 year ago
Thats awesome!
Comment · 1 year ago
So cool!

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton