Hacker Newsnew | past | comments | ask | show | jobs | submit | 0xd1r's commentslogin

Can it perform DOM manipilation as well, like fill forms or would the LLM response need to be structured for each specific site to use it on? And would an LLM be able to perform such a task?


It can fill forms - the agent can invoke a large number of tools to both observe and interact with a page


How does it do so? Just DOM manipulation, viewport scanning or something of the sort?


https://www.indiatoday.in/india/video/exclusive-journalist-s...

In reference to an interview of Pakistan's Defence Minister on Sky. If a country's own minister speaks of harboring terrorists, I think that is evidence enough.


> As part of our IMO work, we also experimented with a natural language reasoning system, built upon Gemini and our latest research to enable advanced problem-solving skills. This system doesn’t require the problems to be translated into a formal language and could be combined with other AI systems. We also tested this approach on this year’s IMO problems and the results showed great promise.

Wonder what "great promise" entails. Because it's hard to imagine Gemini and other transformer-based models solving these problems with reasonable accuracy, as there is no elimination of hallucination. At least in the generally available products.


I don't think that's what they mean.

They explicitly stated that to achieve the current results, they had to manually translate the problem statements into formal mathematical statements:

> First, the problems were manually translated into formal mathematical language for our systems to understand.

How I understand what they're saying is that they used gemini to translate the problem statement into formal mathematical language and let DeepMath do it's magic after that initial step.


I suppose they are using keras because of its simplicity. But I agree, things have really moved on from keras.


One of the best passion projects I've seen. Love that there's so many one-click deploy options.


Thanks! One of the main goals was ease of deployment for non-tech folks. I'll be adding more deployment options over the coming weeks too.


Indeed, quite lovely to see. Wish someone did a piece on 'Metro Gali', where there are people like this for cameras.


Ironic that this article is paywalled. Here's a non-paywalled link: https://archive.is/0C0RQ


Not really, that fact supports the premise of the article.


But then fewer people can read it and the author's arguments reach a smaller audience, which does seem like a major disadvantage.


They should put open it up for free to reach the maximum audience, but to compensate for the lost revenue they could get a company to fund the article in exchange for prominently placing an image or text about said company ...


Also disabling JS works.

And if that is a hassle my little hack to selectively view pages with js disabled works great here https://noscript.it/?p=0#https://www.economist.com/business/...


"Social networks are not the only medium allowing the group that advertisers most covet—the better-off with money to splurge—to wriggle beyond their reach"

I wonder what the median disposable income of people who use archive links to circumvent paywalls is?


This reiterates the same fallacious argument large corporations use to put one over open-source. And since it sounds plausible to the layman, it is parroted by them. Quite shocking to see another example out and about.


Wasn't 1965, part of ALGOL W, but somewhere in the previous millenium, in a language meant for object-oriented tax collection.


I'm hoping that this is a commit that is reverted back, after some amount of backlash from the community, if at all this was intentional.

Else, it evokes the sentiment of riskynacho on the comment, "It's almost like DuckDuckGo wants to eliminate itself from being a safe useful alternative in the search engine competition."


Backlash won't matter since this is most likely due to a change in the underlying Bing API they are getting their search results from.


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

Search: