Rendered at 19:13:17 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
mattaustin 1 hours ago [-]
I submitted a remote code execution to the browser-use about 40 days ago. GHSA-r2x7-6hq9-qp7v
I am a bit stunned by the lack of response. Any safety concerns in this project?
19 minutes ago [-]
LarsenCC 34 minutes 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.
syl5x 2 hours ago [-]
That's pretty good, I've achieved pretty much the same thing using the vercel's agent-browser, but I've tried playwright and it worked easily as good. Its good for scraping, automating stuff in the browser.
reaganhsu 43 minutes ago [-]
agent-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
debarshri 2 hours ago [-]
I think the usecase here is to go beyond scraping. I think you can use it as a tool for agent harnesses and make it part of a larger workflow.
embedding-shape 1 hours ago [-]
> The new paradigm? SKILL.md + a few python helpers that need to have the ability to change on the fly. [...] What would you call this new paradigm? A dialect?
It's called "agentic coding" for all I know, and isn't a new paradigm, the whole purpose with agentic coding is that it uses tools to do their thing, then those tools could be structured as the good old JSON schema tools next to the implemented runtime, or as MCP, or HTTP API or whatever, the "paradigm" is the same: Have a harness, have a LLM, let the harness define tools that the LLM can use those.
codethief 25 minutes ago [-]
IIUC the point is that the agent has the ability to modify itself? So one possible term could be "self-evolving" or "self-modifying agent".
embedding-shape 24 minutes ago [-]
Any agent that accepts "work in this working directory" (which AFAIK, all of them do) have had this ability, even the initial GPT2/3 experiments around matching LLMs with primitive tool-calling.
SomewhatLikely 28 minutes ago [-]
If I'm understanding correctly, this might be the first example of just-in-time agentic coding that I've come across.
amelius 1 hours ago [-]
I was wondering when someone would finally build this.
Anyway, of course this will be superseded by a harness that provides freedom to complete any task within the OS.
reaganhsu 47 minutes ago [-]
it will be crazy when someone builds this
esafak 15 minutes ago [-]
1. Can you elaborate on the self healing aspect of it?
2. Can you publish a tabular comparison on your README?
3. What information gets sent to your API server?
mvelbaum 2 hours ago [-]
Sawyer Hood's dev-browser[0] allows the browser to write playwright JS code directly. Do you have cases where his approach fails and yours works?
It's called "agentic coding" for all I know, and isn't a new paradigm, the whole purpose with agentic coding is that it uses tools to do their thing, then those tools could be structured as the good old JSON schema tools next to the implemented runtime, or as MCP, or HTTP API or whatever, the "paradigm" is the same: Have a harness, have a LLM, let the harness define tools that the LLM can use those.
Anyway, of course this will be superseded by a harness that provides freedom to complete any task within the OS.
2. Can you publish a tabular comparison on your README?
3. What information gets sent to your API server?
[0] https://github.com/SawyerHood/dev-browser
There's still plenty that Browser-Use could improve in terms of stealthiness.
We didn't detect it using CDP (good!) but can still detect that it is Browser-Use.