alt Hacker NewsI built an AI "web harness" running on a sandboxed Chromium (using a custom side-loaded plugin that talks over websockets to a "driver") to basically do anything a normal user could do in a browser. It totally bypasses any and all bot measures and only gets the ones you yourself would get as well (and passes those successfully, e.g. Cloudflare checkbox or those annoying OCR puzzles).
Not sure if I should release it, but I'm sure more people are catching onto the power of agentic browsing.
Replies
Thanks for letting us know that we need a new layer of detection systems.
Also it’s great(!) to see that we’re going from “but ethics” to “I got mine, who cares”.
Humans are interesting creatures.
Edit: Please before assuming that I'm assuming things, this is an observation I'm making over time. It's possible that I'm in a bubble, but it's not a sample size of 1 (i.e. The comment I replied only).
the 4get dev did the same thing a little while ago for his metasearch engine: https://git.lolcat.ca/lolcat/4play
Camoufox bypasses most blocks with no problems https://camoufox.com/
FYI Muse smashes through those captchas natively without prompting.
Right, but what happens when everyone uses that at scale? Without agreements and standards it isn't pretty.
anyone can spin these kind of side projects and do easy talk, but the moment you actually try to use this on signed-in Linkedin or Amazon its going to fail
the only solution is to drive your regular browser with all your sessions/cookies via an extension
Interesting, how is the chromium sandboxed? profile dir cli param? or deeper like chromium engine framework embeded in the application?
By describing it here you've already released it no?
(using a custom side-loaded plugin that talks over websockets to a "driver")
Is that necessary? You could start Chromium with an open debug port and use Chrome Devtools Protocol to send commands.