I don't believe it does give them your credentials? It's more like running something like AutoHotkey and having it send screenshots to Perplexity and inject whatever input events they send back, but integrated directly into the browser instead of running as a separate program.
They are not interacting with Amazon at all. They are sending control commands to your computer, where you've opened a session logged into Amazon as you. Amazon is claiming they can't run commands on your computer.
The whole thing becomes entirely absurd if you consider that a cloud model isn't even fundamental to the setup; you could just as well slot in a local model or codex or anything else and the scenario would be exactly the same. Perplexity is just acting as a model provider here.
I know it feels like they're different, but I think that at its core, they're the same.
When you say I am "manually controlling the site", that actually means I run a program on my computer that makes requests to the site, chooses how to display the content provided by the site, and then gives me control mechanisms (e.g. clicking, scrolling) to interact with that content.
An "agentic workflow" does the same thing. It's a computer program that I run that makes requests to the site, chooses how to display the content provided, and then gives me control mechanisms (e.g. typing text) to interact with the content.
I'm not trying to be pedantic here. I really think that the two aren't that different.
Comet IS a normal chromium browser. The assistant thing is just a chat on the right sidebar and you can tell it stuff like “click around on this website to do X”, which it can then do for a limited amount of turns
> What about giving it to your secretary with a list of what to shop?
"When a Comet user directs the Assistant to locate an item on Amazon.com, the Assistant takes screenshotsof the browser view, sends those screenshotsfrom the user’s computer to Perplexity’s servers, and receives instructions from Perplexity’s servers on how to navigateAmazon.com. In other words, the Assistant cannot operate wholly independently; it relies on direction from the user and instructions from Perplexity’s servers."
Obviously all browsers rely on direction from the user. But they also typically rely on instructions from the browser maker's servers. Traditionally, you get all of those instructions in a single download that's been pre-packaged (the browser program itself). But if part of the browser's logic requires more computational resources than most consumers have, what's the problem with "outsourcing" that bit to Perplexity's servers?
As a consumer, I don't think it's very prudent to trust a company with that kind of access to your data, but it doesn't seem materially different from the kind of trust you have to give to Chrome.
> if part of the browser's logic requires more computational resources than most consumers have, what's the problem with "outsourcing" that bit to Perplexity's servers?
It's not longer my agent. It's a joint agent of my self and whoever else is giving it instructions. (This is Amazon's argument.)
Also, Amazon told Perplexity to fuck off. If your assistant is told to stop doing something in a cease and desist, and then keeps doing it, the fact that you asked them to do it isn't a get-out-of-jail-free card.
My guess is we'll find a balance where local models can act as user agents while corporate ones have to meet certain requirements to gain that safe harbour.
He doesn’t need to “grab the wheel”. Simply saying “go-around” would have been enough, it’s highly highly unlikely that the captain would have ignored that.
Yes I was wrong. Looking at the transcript that go-around call out was likely from the PF; that's where the data recorder indicates the brakes were released the throttle set to max for the go-around (and go back to braking only 4 sec later).
Still, the PM notified PF that they were going too fast many times during the approach. All warnings were ignored.
I also take my shoes and off and find it gross when people don’t.
That said, I don’t think it’s really rational. Our houses are full of bacteria and dirt one way or another anyway. It’s impossible to avoid that without having some kind of airlock equipped with a shower in your porch.
I think it has or had practical reasons. It rains a lot in Japan, and its prime occupation used to be flooded field rice farming. So it is/was normal for shoes coming home to be in a somewhat gross state.
Old farmer style houses in Japan have an entrance area behind the main sliding doors in bare soil[1], and a wooden platform at waist height between it to hallways. The platform can be sat on to take off shoes or to drop off bags of produces, and then hallways and tatami matted areas are further raised an inch or two - the walking floor level of houses are therefore give or take a whole feet off the ground. These together create multiple mental boundaries for dirtiness.
Modern houses have it miniaturized into just a cinder-block high gap or sometimes just industrial colored tiles before a bump. But IMO it's still nice being able to leave wet shoes and umbrellas there.
1: 土間 or doma, meaning soil-space. Oddly this transliteration coincides with "home" in Russian(and of course rhymes with Latin domus).
I think these practices come from more rural but also tropical origins?
One part is purely practical, making it easier to keep the living space clean when you are coming in from the farm etc. Places with messy winters have similar concepts for muddy boots, snow boots, etc.
Some regions also have (or historically had) real risk of parasite transmission from soil and short grass. Taking off shoes reduces the chance of bringing their eggs or tiny larva into your living space.
I can imagine some cultural practices here being early memetic/evolutionary in nature, much like some religions codifying what are essentially food-safety rules from a time before microbiology was scientifically understood. We think about the parts we can see, but also have some instincts and practices that seem aligned with threats we can't actually sense.
> That said, I don’t think it’s really rational. Our houses are full of bacteria and dirt one way or another anyway.
True, but I don't know about you, but we don't have literal rocks, sediment, dirt pee, or literal poop on our floors in our home, anywhere. But shoes do occasionally step on stuff like that no matter how small, and neither of those things I want inside of my house on the floor.
But you're right that there still is bacteria or dirt all over the place, no doubt. But still, I don't step on something slightly soft with my socks in the living room and then inspect my foot to find poop stuck to it, and I think I'm gonna continue to prefer this way.
> This is basically what dust is. It’s everywhere.
What?
> Dust in homes is composed of about 20–50% dead skin cells.[2] The rest, and in offices and other built environments, is composed of small amounts of plant pollen, human hairs, animal fur, textile fibers, paper fibers, minerals from outdoor soil, burnt meteorite particles, and many other materials which may be found in the local environment.[3]
Further: dust is floating in the air and can be removed with decent (MERV ≥11) air filters in your HVAC system. Stuff on the bottom of your shoe makes contact with your floor and stick around until you wash it (and for much longer in the fibre of carpet or rugs).
Where do you live, where dust and pee/poop is the same? I'm fine with having small amount of the former inside, it's unavoidable, but the second is avoidable by removing your shoes.
It is ok that you feel this way. As explicitly stated the report is _generated_ and id does require a different mindset to read AI generated reports. It contains quite a bit of information about attacker behavior and details of the timeline. It also linkes to a story that is now largely human narrated and I´ll keep improving on that as I find time. Having to juggle three separate issues yesterday did not leave much time for manual writeups.
reply