371–380 of 433 posts
I am curious to know usecases of this agentic browsers.
Earlier quoted context omitted.
I don't believe it's possible to give an LLM full access to your browser in a safe way at this point in time. There will need to be new and novel innovations to make that combination safe.
People directly give their agent root, so I guess it is ok.
Take the flight booking as an example? Why has flight booking become so obsfucated and annoying that people want an agent booking for them?
Why can't that agent just query an API to get the best available information?
It's just turtles all the way down at this point, when a user wants more fine grained interaction, the agent can design a frontend to visualise the information in a more structured way, then when that inevitably becomes obsfucated due to travel companies noticing a 0.1% reduction in revenue, we need to build another agent on-top of the agent to help further simplify down the information.
Agents upon agents upon agents
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)
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)
All of this agent navigation of browsers feels like a self-made issue. Take the flight booking as an example? Why has flight booking become so obsfucated and annoying that people want an agent booking for them? Why can't that agent just query an API to get the best available information? It's just turtles all the way down at this point, when a user wants more fine grained interaction, the agent can design a frontend…
Money. The currently process is beneficial for airlines. People end up spending more than they need to, and they profit from it. They have teams who are purposely obfuscating the process to push the average purchase prices up.
It's the same for everything now. Profits for shareholders are priority #1.
It is clear that a lot of things: programming languages, websites and others will have to be adapted to be easier to use for LLMs. Now they are optimized for humans, but I think very soon they will be optimized for LLMs instead.
Programming languages and documentation probably will be. But websites have been pushing in the other direction making themselves as hard as possible to automate or scrape. I suspect every website will nail down the process of uniquely identifying every user and banning anyone using bots to spam or scrape. Why would any website want to allow automated browsers? LLMs don't click on adverts, they don't buy things, they…
According to their own blog post, even after mitigations, the model still has an 11% attack success rate. There's still no way I would feel comfortable giving this access to my main browser. I'm glad they're sticking to a very limited rollout for now. (Sidenote, why is this page so broken? Almost everything is hidden.)
well, at least they are honest about it and don't try to hide it in any way. They probably want to gather more real world data for training and validation, that's why this limited release. openai have browser agent for some time already but I didn't hear about any security considerations. I bet they have the same issues
Seems more likely they’re trying to cover their own ass, so when anything inevitably goes wrong they can point and say “see, we told you it was dangerous, not our fault”.