231–240 of 433 posts
> Anthropic says it hopes to use this research preview as a chance to catch and address novel safety risks; however, the company has already introduced several defenses against prompt injection attacks. The company says its interventions reduced the success rate of prompt injection attacks from 23.6% to 11.2%.
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…
The LLM should not be seeing the raw DOM in its context window, but a highly simplified and compact version of it. In general LLMs perform worse both when the context is larger and also when the context is less information dense. To achieve good performance, all input to the prompt must be made as compact and information dense as possible. I built a similar tool as well, but for automating generation of E2E browser t…
Turned out my prediction was wrong that the big lab’s wouldn’t release a browser with cross-site access before it was safe: https://news.ycombinator.com/item?id=45004846 > Anthropic says it hopes to use this research preview as a chance to catch and address novel safety risks; however, the company has already introduced several defenses against prompt injection attacks. The company says its interventions reduced the…
Earlier quoted context omitted.
This is what they need for the next generation of models. The key line is: > We view browser-using AI as inevitable: so much work happens in browsers that giving Claude the ability to see what you're looking at, click buttons, and fill forms will make it substantially more useful. A lot of this can be done by building a bunch of custom environments at training time, but only a limited number of usecases can be handle…
I don’t get the argument. Why is the loaded foot gun better in the hands of “select” customers better than in the hands of self selecting group of beta testers?
Earlier quoted context omitted.
I wonder how this will even fare in the review process, or if the big AI players will get a free pass here. My intuition says that it's a risk that Google/Chrome absolutely don't want to own, it will be curious to see how "Agentic" AI gets deployed in browsers from a liability fallout perspective.
Probably no liability considering that is how other phishing attempts are viewed.
I think this is more akin to say a theoretical browser not implementing HTTPS properly so people's credentials/sessions can be stolen with MiTM attacks or something. Clearly the bad behavior is in the toolchain and not the user here, and I'm not sure how much you can wave away claiming "We told you it's not fully safe." You can't sell tomatoes that have a 10% chance of giving you food poisoning, even if you declare that chance on the label, you know?
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…
It is kind of funny how the systems are set up where there often is dense and queryable information out there already for a lot of these tasks, but these are ignored in favor of the difficult challenge of brute forcing the human consumer facing ui instead of some existing api that is designed to be machine readable already. E.g. booking flights. Travel agents use software that queries all the airlines ticket inventor…
Earlier quoted context omitted.
I am starting to see this age of internet-for-robots-by-robots as our second chance to detach from those devices and start living irl again.
Just the pesky matter of figuring out what humans will do for money, and then we'll be free to run in the meadows like we were meant to
Don't get me wrong I'm not trying to flippant about the potential for destroyed value here. Many industries (like journalism*) really need to figure this out faster, the advertising model might collapse very quickly when people lose trust that they're reading Human created and vetted material. And there will be broader fallout if all these bonkers AI investments fail to pay off.
[*] Though for journalism specifically it feels like we as a society need to figure out the trust problem, we're rapidly approaching a place of prohibitively-difficult-to-validate-information for things that are too important to get wrong.
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…