Live data from Hacker News

Claude for Chrome

anthropic.com

331–340 of 433 posts

Re: Claude for Chrome

#331

Fuck google. Fuck chrome. Enough of these bastards making the web their playground. Revolutions must start somewhere, HN is full of bright people, let’s not get fooled so easily with shiny toys.

lmao, HN is full of people who make a living building the things you want to revolt against.

this forum is an echo chamber for over paid boot lickers.

Re: Claude for Chrome

#332

Claude for Chrome seems to be walking right into the "lethal trifecta." https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/ "The lethal trifecta of capabilities is:" • Access to your private data —one of the most common purposes of tools in the first place! • Exposure to untrusted content —any mechanism by which text (or images) controlled by a malicious attacker could become available to your LLM • The abilit…

I wonder if one way to mitigate the risk would be that by default the LLM cant send requests using your cookies etc. You would actively have to grant it access (maybe per request) for each request it makes with your credentials. That way by default it can't fuck up (that bad) and you can choose where it is accetable to risk it (your HN account might be OK to risk but not your back account)

Re: Claude for Chrome

#333
post #284

Earlier quoted context omitted.

I think Simon has proposed breaking the lethal trifecta by having two LLMs, where the first has access to untrusted data but cannot do any actions, and the second LLM has privileges but only abstract variables from the first LLM not the content. See https://simonwillison.net/2023/Apr/25/dual-llm-pattern/ It is rather similar to your option (b).

Can't the attacker then jailbreak the first LLM to generate jailbreak with actions for the second one?

If you read the fine article, you'll see that the approach includes a non-LLM controller managing structured communication between the Privileged LLM (allowed to perform actions) and the Quarantined LLM (only allowed to produce structured data, which is assumed to be tainted).

See also CaMeL https://simonwillison.net/2025/Apr/11/camel/ which incorporates a type system to track tainted data from the Quarantined LLM, ensuring that the Privileged LLM can't even see tainted _data_ until it's been reviewed by a human user. (But this can induce user fatigue as the user is forced to manually approve all the data that the Privileged LLM can access.)

Re: Claude for Chrome

#334

I built a very similar extension [1] a couple of months ago that supports a wide range of models, including Claude, and enables them to take control of a user's browser using tools for mouse and keyboard actions, observation, etc. It's a fun little project to look at to understand how this type of thing works. It's clear to me that the tech just isn't there yet. The information density of a web page with standard rep…

How do screen readers work? I’ve used all the aria- attributes to make automation/scraping hopefully more robust, but don’t have experience beyond that. Could accessibility attributes also help condense the content into something more manageable?

Re: Claude for Chrome

#335

I don’t know if this will make anything better. Internet is now filled with ai generated text, picture or videos. Like we havent had enough already, it is becaming more and more. We make ai agents to talk to each other. Someone will make ai to generate a form, many other will use ai to fill that form. Even worst, some people will fill millions of forms in matter of second. What is left is the empty feeling of having…

I've had this conversation a couple of times now. If AI can just scan a video and provide bullet points, what's the point of the video at all? Same with UI/UX in general. Without real users, then it starts to feel meaningless. Some media is cool because you know it was really difficult to put it together or obtain the footage. I think of Tom Cruise and his stunts in Mission Impossible as an example. They add to the s…

> If AI can just scan a video and provide bullet points, what's the point of the video at all?

Maybe, just maybe, the video format is being abused. Blogs are much more time-efficient. Frankly, every time I see some interesting topic linked to a video, I just skip it. I don't have the time or will to listen to some "content creator" blabbering to increase their video length/revenues. If I'm REALLY interested, I just use some LLM to summarize it. And no, I don't feel bad for doing this.

Re: Claude for Chrome

#336
post #300

Earlier quoted context omitted.

How would you go about making it more secure but still getting to have your cake too? Off the top my head, could you: a) only ingest text that can be OCRd or somehow determine if it is human readable b) make it so text from the web session is isolated from the model with respect to triggering an action. Then it's simply a tradeoff at that point.

In the future, any action with consequence will require crypto-withdrawal levels of security. Maybe even a face scan before you can complete it.

Ahh technology. The cause of, and _solution to_, all of life’s problems.

Re: Claude for Chrome

#338
post #321

Earlier quoted context omitted.

That’s easy. Giving my parents a safe browser to utilize without me is the challenge.

Because there never were safe web browsers in the first place. The internet is fundamentally flawed and programmers are continously having to invent coping mechanisms to the underlying issue. This will never change.

You seem like the guy, who would call car airbags a coping mechanism.

Re: Claude for Chrome

#339
For someone who does not uses Chrome as a personal browser I am very excited.

I use Chrome only for development it this would probably help with the debugging problems, finding reproduction steps and writing website flows and QA steps much easier.

Obviously I would never use this on the browser with all my private sessions active as it is a huge vulnerability risk as well as not a fan of all my data being sent straight to CIA/Mossad.

Post reply on HN