Smooth
AI
browser agent api
SHOW HN2025
How HN took it
3 positive, 10 neutral or asking, 0 mixed, 2 critical, out of 15 comments about the project. Thread score +0.17.
Performance: 1 for, 0 againstExecution: 1 for, 0 againstIdea: 0 for, 1 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fast demo performance
From 1 comment
Super impressive demo. Seems a lot faster than alternatives. How did you achieve that?
ayushr1 on HN
Complex prompt handled well
From 1 comment
I just wrote a complex prompt and it did a good job. How do you do evals or testing of your project?
ukulerok on HN
Objections
Browser agents vulnerable to prompt injection; mitigations insufficient
From 2 comments
> 2. We have a critic LLM that assesses among other things whether the website content is leading a non-aligned initiative. This is still subject to the LLM intelligence, but…
creatonez on HNHi, thanks for sharing. My main concern with these browser agents are how are they handling prompt injection. This blog post on Perplexity's Comet browser comes to mind:…
jasonriddle on HN
Seems like spambot tooling given proxy rotation and CAPTCHA solving
From 1 comment
So you're shamelessly selling spambots? The marketing here is wild... "proxy rotation"... "auto-CAPTCHA solvers"
creatonez on HN
Requests
Support for deterministic extractor scripts
From 1 comment
Do you support writing deterministic extractor scripts? I want to use an agent like this primarily as a way to help me write and refine deterministic extraction scripts, rather…
TheTaytay on HN
Sign up without Google SSO
From 1 comment
Is there a way to sign up without Google SSO?
PhilippGille on HN
Questions
How is prompt injection handled
From 1 comment
Hi, thanks for sharing. My main concern with these browser agents are how are they handling prompt injection. This blog post on Perplexity's Comet browser comes to mind:…
jasonriddle on HN
How LLM-Ex is structured
From 1 comment
Really interesting work! I have two questions: 1.LLM-Ex > We call this LLM-Ex. Could you share more about the internal structure of LLM-Ex? Is it something like a fixed XML-style…
ekusiadadus on HN
How evals and testing are done
From 1 comment
I just wrote a complex prompt and it did a good job. How do you do evals or testing of your project?
ukulerok on HN
Alternatives named
Browser Use
From 1 comment
Perplexity Comet
From 1 comment
Hi, thanks for sharing. My main concern with these browser agents are how are they handling prompt injection. This blog post on Perplexity's Comet browser comes to mind:…
jasonriddle on HN
Claude for Chrome
From 1 comment
Hi, thanks for sharing. My main concern with these browser agents are how are they handling prompt injection. This blog post on Perplexity's Comet browser comes to mind:…
jasonriddle on HN