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

Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

anthropic.com

Post reply on HN
Print view View original

711–720 of 758 posts

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#711

Post by pxlwdth »

pc86 wrote: post #668
aduffy wrote: post #374

Earlier quoted context omitted.

This has existed for a long time, it's called "RPA" or Robotic Process Automation. The biggest incumbent in this space is UiPath, but there are a host of startups and large companies alike that are tackling it. Most of the things that RPA is used for can be easily scripted, e.g. download a form from one website, open up Adobe. There are a lot of startups that are trying to build agentic versions of RPA, I'm glad to s…

Is "AI SaaS bro discovers not everything has a JSON API" the new "startup bro just reinvented a bus"?

Good one.

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#712

Post by jameslholcombe »

bonoboTP wrote: post #709
idopmstuff wrote: post #700

Earlier quoted context omitted.

It's basically the digital equivalent of humanoid robots - people object because having computers interact with a browser, like building a robot in the form of a human, is incredibly inefficient in theory or if you're designing a system from scratch. The problem is that we're not starting from scratch - we have a web engineered for browser use and a world engineered for humanoid use. That means an agent that can use…

Yes, but my friend would say, all these websites/software should just publish an API and if they don't that's just incompetence/laziness/stupidity. But a "should" doesn't matter. Changing human nature is so immensely difficult, but it feels easy to say "everyone should just [...]". Seems to be a gap in thinking that's hard to bridge.

We took this approach at Industry Dive already because of these reasons. diveaccess.com

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#713

Post by alexey-salmin »

acchow wrote: post #710
bonoboTP wrote: post #691

I've been saying this is coming for a long time, but my really smart SWE friend who is nevertheless not in the AI/ML space dismissed it as a stupid roundabout way of doing things. That software should just talk via APIs. No matter how much I argued regarding legacy software/websites and how much functionality is really only available through GUI, it seems some people are really put off by this type of approach. To me…

> and how much functionality is really only available through GUI Isn't the GUI driven by code? Can anything at all in the GUI work that can't be done programmatically?

The code behind the GUI can be arbitrarily obscure. The only reliable way to understand its meaning in a general case is to run it and look at the rendered image. Trying to build a model that implicitly develops an alternative implementation of a browser inside of it sounds worse that just using an existing browser directly.

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#714

Post by randito »

idopmstuff wrote: post #700
bonoboTP wrote: post #691

I've been saying this is coming for a long time, but my really smart SWE friend who is nevertheless not in the AI/ML space dismissed it as a stupid roundabout way of doing things. That software should just talk via APIs. No matter how much I argued regarding legacy software/websites and how much functionality is really only available through GUI, it seems some people are really put off by this type of approach. To me…

It's basically the digital equivalent of humanoid robots - people object because having computers interact with a browser, like building a robot in the form of a human, is incredibly inefficient in theory or if you're designing a system from scratch. The problem is that we're not starting from scratch - we have a web engineered for browser use and a world engineered for humanoid use. That means an agent that can use…

Totally agree. A general-purpose solution that ties together different messy interfaces will win in the long run -- i.e the IP protocol, copy-paste, browsers. In these cases, they provide a single-way for different aspects of computing to collaborate. As mentioned before, semantic web initiatives did not succeed and I think there's an important lesson there.

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#715

Post by alwayslikethis »

acchow wrote: post #710
bonoboTP wrote: post #691

I've been saying this is coming for a long time, but my really smart SWE friend who is nevertheless not in the AI/ML space dismissed it as a stupid roundabout way of doing things. That software should just talk via APIs. No matter how much I argued regarding legacy software/websites and how much functionality is really only available through GUI, it seems some people are really put off by this type of approach. To me…

> and how much functionality is really only available through GUI Isn't the GUI driven by code? Can anything at all in the GUI work that can't be done programmatically?

More often than not you don't have access to the underlying code, or the vendor has interest against you being able to automate it since the complexity is a part of their business model.

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#718

Post by hugocbp »

Axsuul wrote: post #488
hugocbp wrote: post #11

Great work by Anthropic! After paying for ChatGPT and OpenAI API credits for a year, I switched to Claude when they launched Artifacts and never looked back. Claude Sonnet 3.5 is already so good, specially at coding. I'm looking forward to testing the new version if it is, indeed, even better. Sonnet 3.5 was a major leap forward for me personally, similar to the GPT-3.5 to GPT-4 bump back in the day.

How are you using it with coding?

Usually I create a Project in the UI, upload some files I think might be relevant, and just start asking things like refactoring, how can it improve the code, how to test (or which edge cases might be missing in the test files).

Once we get going, I start asking how can we change the code to do what I need to do, etc.

After the history gets too long and Claude starts bugging me about limits, I ask it to summarize the context of the whole conversation, and add that to the Project and start a new chat.

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#719

Post by fivestones »

csomar wrote: post #561

I like its lazy approach > I apologize, but it seems we're having some issues installing Chromium. As an alternative, since I can see Firefox is already installed on the system, would you like to use Firefox instead? Or would you prefer me to try a different approach to installing Chromium? It seems unable to figure out how to install chormium. Sees the Firefox icon out there and just want to use it. You know, like a…

So meta! I love this story

Re: Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku

#720

Post by mergisi »

My First Experience with Claude Computer Use - It's Mind-Blowing!

Just tested Claude's new Computer Use feature and had to share this simple but powerful test:

My Basic Prompt: "Please: 1. Search Amazon for 3 wireless earbuds: Find price Rating Brand name

2. Make a simple Excel file 'earbuds.xlsx': Put the information in a basic table Add colors to the headers Sort by price

3. Show me the results"

What blew my mind: - Claude actually looked at my screen - Moved the mouse by itself - Clicked buttons like a human - Created reports automatically

It's like having a virtual assistant that can really use your computer! No coding needed - just simple English instructions.

For those interested: https://mergisi.medium.com/8f56f683e307

Post reply on HN