For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | handfuloflight's commentsregister

Maybe an icon on hover or a small static icon but the latter could get repetitive, the hover would solve the repetition.

My jaw did drop. This could pair really well with a hybrid bread crumb + menu that gives you an escape hatch or granular on demand traversal. Love it!

Thank you!!

Slop is just what you are not expending calories on to bring into your cognitive workspace.

Who will investigate it? Who will do anything about it? What can be done?

Why should anything be done? This is what America voted for.

We get another vote in November. Americans can express whether they think this was a good idea or not. If they aren't overwhelmingly opposed to it, then democracy has spoken.

At that point it will be up to the rest of the world to decide what to do about a nation that has, and will continue to, invade other countries, apparently unprovoked.


The rule of law should apply to everyone, if government officials are breaking the law and being protected by the executive branch that's a sign of deep disfunction in your system

Jeebus, this is dark.

This is why I can't vote.

I can't give my ethical status as a human over to what the masses of folks in the US think is okay. It's kind of a disgusting proposition.

Like, you who are in the thuick of it, you who have given your voice over to empire, you expect the rest of the world to do something about the horrors done in your name just because... what?

The assholes you live around "voted" to do something evil, lesser or greater?

And now you're doing evil, too? And it is, somehow, "up to the rest of the world?"

That's bleak and you really should think if "democracy" (or it's pale ghost that haunts US politics) is doing anything useful for your status as an ethical human.

It's entirely possible that you indeed do have such a boot on your neck that you really can't resist the power of empire in its core, but for [insert your preferred diety here]'s sake, you don't have to roll your soft belly over and take the kicks.


Yeah. I vote for the lesser evil. My ethical status is less important to me than trying to make the world a better place, even if imperfectly.

I believe that my ethical status would be in more jeopardy right now if I could have prevented a clearly criminal war, and chose not to. My actions, not the actions of others, determine my ethical state.

It does mean I face an ethical quandary now. Thus far I have upheld the social contract of democracy. I have not broken it in an attempt to end this war. That is an ethical stain on me, which I live with as best I can. It is my inaction, not the actions of the country, which stain me.

I will vote again when I can, and right now I'm going to hope that ends the war. That will not be sufficient, but one of my moral principles is "It is not your duty to finish the work, but neither are you at liberty to neglect it".

If it suffices... then it suffices, and I will do my best with what happens after that. If it does not suffice, then I will be faced with an even worse moral quandary, and I hope I find the strength to do whatever seems right in that dire circumstance.


I recommend Jon Stewart's podcast with Heather Cox Richardson from this week. They talk about the ceding and concentration of power, and how we the people can take ours back. Not something that can happen in a midterm or maybe even the next ten years. But at least we are talking about it more and their words will help us articulate things better to our neighbors.

https://www.youtube.com/watch?v=gwX9wC6Ov2Y


The people that investigate Trump are fired or pushed out

How does this compare to https://github.com/alibaba/page-agent?


PageAgent doesn't have the strong page understanding - semantic tree representation of the pages - it's just a flat DOM basic stripping of HTML - which makes it hard to navigate shadow DOMs, even same origin iframes for that matter or diff frameworks. And also they do element marking - CUA style not sure if they use it in the actual calls to Qwen. And yeah, as arjun takes 30 steps to even do a basic task of find some info.

What we strengthened building agents working on 2M+ web workflows in the past 4 months - is our representation of pages that seamlessly helps agents go through any page old to new iframes, shadow-DOMs and more. Best part of Rover if you as website owner enable cross-origin reqs, say Doordash has Rover and a merchant be like get my restaurant menu from my website and update in Doordash. Rover agent determines the 3P website need, launches our cloud browser to securely execute 3P site actions gets the menu and updates the merchant menu on Doordash so your users never have to leave your site to do a task - one of a kind enabling cross-site interactions


Also PageAgent's DOM based understanding is pretty simple and based on top of Browser-Use's approach.

On the other hand we construct our own custom Agent Accessibility Trees to represent webpages to models. This approach leads to twice as good performance in WebBench of 300+ tasks (81% vs 40%)


I appreciate the responses and will be looking deeply into Rover. Thank you.


I actually tried out PageAgent it was reaaaally slow, and not that accurate.

You can actually try it out on our own site rtrvr.ai


Can you run this in another sandbox? Not sure why you'd want to... but can you?


Nested page tables / nested virtualization made it to consumer CPUs about a decade ago, so yes :)


It's pretty common to run VMs within containers so an attacker has to escape twice. You can probably disable 99% of system calls.


You can also not click on links you are not interested in. Is that difficult?


The ToS you agreed to gives Anthropic the right to modify the product at any time to improve it. Did you have your agent explain that to you, or did you assume a $200 subscription meant a frozen product?


I understand. Just with AI, I don't think the behavior should change so drastically. Which I understand is paradoxical because we enjoy it when it can 10x or 1000x our workflow. I think responsible AI includes more transparency and capability control.


You rent ai, you don’t own it (unless you self host).


That ship has sailed. These models were trained unethically on stollen data, they pollute tremendously and are causing a bubble that is hurting people.

"Responsible" and "Ethic" are faaar gone.


How does your memory engine actually work?


Hey Husain here, co founder of Modulus Can talk about this for hours but heres a summary Every repo added by the user is analyzed for technical specifications which are stored without the code itself. Updated every time a significant change is made to the codebase. These are used at the time of retrieval by checking for relevance of the connected repos and extracting them as relevant context to the ongoing task. Hope that answers your question!


Excellent share! Danke.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You