Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude for Chrome

anthropic.com

Post reply on HN
Print view View original

421–430 of 433 posts

Re: Claude for Chrome

#421

Post by xenobeb »

falcor84 wrote: post #103
strange_quark wrote: post #18

Earlier quoted context omitted.

It's insane how we're throwing out decades of security research because it's slightly annoying to have to write your own emails.

> it's slightly annoying to have to write your own emails. I find that to be a massive understatement. The amount of time, effort and emotional anguish that people expend on handling emails is astronomical. According to various estimates, email-handling takes somewhere around 25% of the work time of an average knowledge worker, going up to over 50% for some roles, and that most people check and reply to emails on eve…

At my job it takes about 50% of my time. I love LLMs but I don't see how they can possible help me with email.

I would have to write a prompt that is almost exactly the same as writing the email. It is not like I am writing a fictional story that the LLM could somehow compress the main ideas. I feel like the LLM would have to be able to read my mind to properly respond to my inbox.

Re: Claude for Chrome

#422

Post by DrewADesign »

crazygringo wrote: post #411
bluebarbet wrote: post #405

Earlier quoted context omitted.

>It’s not that people don’t have critical thinking skills It isn't? I agree that it's a fallacy to put this down to "people are dumb", but I still don't get it. These AI chatbots are statistical text generators . They generate text based on probability. It remains absolutely beyond me why someone would assume the output of a text generator to be the truth.

Because across most topics, the "statistical text generator" is correct more often than any actual human being you know? And correct more often than random blogs you find? I mean, people say things based on probability. The things they've come across, and the inferences they assume to be probable. And people get things wrong all the time . But the LLM's have read a whole lot more than you have, so when it comes to th…

It’s much easier to judge a person’s confidence while speaking, or even informally writing, and it’s much easier to evaluate random blogs and articles as sources. Who wrote it? Was it a developer writing a navel gazing blog post about chocolate on their lunch break, or was it a food scientist, or was it a chocolatier writing for a trade publication? How old is it? How many other posts are on that blog and does the site look abandoned? Do any other blog posts or articles concur? Is it published by an organization that would hold the author accountable for publishing false information?

The chatbot completely removes any of those beneficial context clues and replaces them with a confident, professional-sounding sheen. It’s safest to use for topics you know enough about to recognize bullshit, but probably least likely to be used like that.

If you’re selling a product as a magic answer generating machine with nearly infinite knowledge— and that’s exactly what they’ve being sold as— and everything is presented with the confidence of Encyclopedia Britannica, individual non-experts are not an appropriate baseline to judge against. This isn’t an indictment of the software — it is what it is, and very impressive— but an indictment of how it’s presented to nontechnical users. It’s being presented in a way that makes it extremely unlikely that average users will even know it is significantly fallible, let alone how fallible, let alone how they can mitigate that.

Re: Claude for Chrome

#425

Post by makeitdouble »

digitaltrees wrote: post #417
makeitdouble wrote: post #291

Earlier quoted context omitted.

This was the Rabbit R1's connundrum. Uber/DoorDash/Spotify have APIs for external integration, but they require business deals and negociations. So how to evade talking to the service's business people ? Provide a chain of Rube Goldberg machines to somewhat use these services as if it was the user. It can then be touted as flexibility, and blame the state of technology when it inevitably breaks, if it even worked in…

This is definitely true but there are more reasons that explain why so many teams choose the seemingly irrational path. First, so many APIs are designed differently, so even if you decide the business negotiation is worth it you have development work ahead. Second, tons of vendors don’t even have an API. So the thought of building a tool once is appealing

Those are of course valid points. The counterpart being that a vendor might not have an API because they actively don't want to (Twitter/X for instance...), and when they have one, clients trying to circumvent their system to basically scrape the user UX won't be welcomed either.

So most of the time that path of "build a tool once" will be adversarial towards the service, which will be incentivized to actively kill your ad-hoc integration if they can without too much collateral damage.

Re: Claude for Chrome

#426

Post by chamomeal »

DrewADesign wrote: post #422
crazygringo wrote: post #411

Earlier quoted context omitted.

Because across most topics, the "statistical text generator" is correct more often than any actual human being you know? And correct more often than random blogs you find? I mean, people say things based on probability. The things they've come across, and the inferences they assume to be probable. And people get things wrong all the time . But the LLM's have read a whole lot more than you have, so when it comes to th…

It’s much easier to judge a person’s confidence while speaking, or even informally writing, and it’s much easier to evaluate random blogs and articles as sources. Who wrote it? Was it a developer writing a navel gazing blog post about chocolate on their lunch break, or was it a food scientist, or was it a chocolatier writing for a trade publication? How old is it? How many other posts are on that blog and does the si…

Well said!! And the hype men selling these LLMs are really playing into this notion. They’ve started saying stuff like “they have phd-level knowledge on every topic”.

Re: Claude for Chrome

#427

Post by originalvichy »

chamomeal wrote: post #388
originalvichy wrote: post #353

Earlier quoted context omitted.

This is exactly the conversation I had with a colleague of mine. They were excited about how LLMs can help people interact with data and visualize it nicely, but I just had to ask - with as little snark as possible - if this wasn't what a monitor and a UI were already doing? It seems like these LLMs are being used as the cliche "hammer that solves all the problems" where problems didn't even exist. Just because we ar…

I’ve been thinking about this a lot too, in terms of signal/noise. LLMs can extract signal from noise (“summarize this fluff-filled 2 page corporate email”) but they can also create a lot of noise around signal (“write me a 2 page email that announces our RTO policy”). If you’re using LLMs to extract signal, then the information should have been denser/more queryable in the first place. Maybe the UI could have been b…

That's a nice way of explaining it. I also feel like some sort of LLM purist by being critical of features that serve only to pollute emails and comms with robotic text not written by an actual person. We will as societies have to come up with a new metric for TL;DR or "this was a perfectly cohesive and concise text", since LLMs have obscured the line.

Re: Claude for Chrome

#428

Post by selinkocalar »

The security model here is going to be interesting. Browser extensions with AI capabilities essentially get access to everything you're doing online. Wonder if they're doing any local processing or if it's all hitting their APIs. The data governance implications for enterprise use could be messy.

Re: Claude for Chrome

#429

Post by victorbjorklund »

johnfn wrote: post #377
victorbjorklund wrote: post #332

Earlier quoted context omitted.

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)

This kind of reminds me of `--dangerously-skip-permissions` in Claude Code, and yet look how cavalier we are about that! Perhaps you could extend the idea by sandboxing the browser to have "harmless" cookies but not "harmful" ones. Hm, maybe that doesn't work, because gmail is harmful, but without gmail, you can't really do anything. Hmm...

Made me think (never gonna happen but still) maybe we could have different cookies/sessions for the agents and for ourself where the webapp can decide what permissions either can have. For gmail maybe you could allow the agent to read your email but not send email and so on.

Re: Claude for Chrome

#430

Post by victorbjorklund »

IsTom wrote: post #375
victorbjorklund wrote: post #332

Earlier quoted context omitted.

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)

Just make a request to attacker.evil with your login credentials or personal data. They can use them at their leisure then.

No reason the agent would have access to the passwords.
Post reply on HN