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

541–550 of 758 posts

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

#541

Post by voidmain0001 »

aledalgrande wrote: post #515
LASR wrote: post #344

This is actually a huge deal. As someone building AI SaaS products, I used to have the position that directly integrating with APIs is going to get us most of the way there in terms of complete AI automation. I wanted to take at stab at this problem and started researching some daily busineses and how they use software. My brother-in-law (who is a doctor) showed me the bespoke software they use in his practice. Runni…

Talking about ancient Windows software... Windows used to have an API for automation in the 2000s (I don't know if it still does). I wrote this MS Access script that ran and moved the cursor at exactly the pixel coordinates where buttons and fields were positioned in a GUI that we wanted to extract data from, in one of my first jobs. My boss used to do this manually. After a week he had millions of records ready to q…

Still present. VB and VB Script would do this by using mouse move to Window handles which were discovered using Spy++. You can do with C# or AutoIT these days.

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

#542

Post by SoftTalker »

sourcecodeplz wrote: post #314
janalsncm wrote: post #271

Reminds me of the rise in job application bots. People are applying to thousands of jobs using automated tools. It’s probably one of the inevitable use cases of this technology. It makes me think. Perhaps the act of applying to jobs will go extinct. Maybe the endgame is that as soon as you join a website like Monster or LinkedIn, you immediately “apply” to every open position, and are simply ranked against every othe…

I've found that doing some research and finding the phone number of the hiring person and calling them directly is very powerful.

Companies still have phone numbers you can call?

I haven't had a phone at work for over 5 years. Nobody can "call" me.

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

#543

Post by quantadev »

javajosh wrote: post #518
quantadev wrote: post #340

Earlier quoted context omitted.

All that's true, and sadly it also often doesn't even matter how good you even are either. I have decades of experience and I still get "evaluated" based on how fast I can do silly brain-teaser IQ-test coding challenges. I've gotten where any company that wants me to do a coding challenge on my own time is an immediate "no thanks" reply from me. Everyone should refuse that. But so many people are so desperate they al…

That error mode (and it is one) doesn't seem so bad, relatively speaking. Personally I find puzzles interesting and while the value is deeply questionable (I mean, how often do you implement binary search or a novel hashing algo at your job?) I actually rather enjoy jumping through those hoops. Far, far worse is just getting ignored entirely. When rejections start looking good, simply because there is some evidence t…

For me I would absolutely never want to work for a company (or boss) who asks people to do a coding challenge before the interview, because that's indicative of a kind of leadership and people I simply don't like. So it's a great filter for me. Once they mention a coding challenge, I end it right then and there, and take them off my list of people wasting my time.

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

#544

Post by cheevly »

brigandish wrote: post #514
cryptoz wrote: post #511

Earlier quoted context omitted.

Prompting is a skill you can develop with practice and get better at. Also, some tasks just aren’t going to work well for various reasons. Yes, LLMs can actually help with coding. But it’s not magic. There are limits. And you get better with practice.

Without people providing their prompts, it's impossible to say whether they are skilled or not, and their complaints or claims of "it worked with this prompt" without the output are also not possible to validate. Maybe there's a clue in there as to why these experiences seem so different. I'm glad GPTs don't get frustrated.

Ive spent thousands of hours, literally, learning the ropes, and continue to hone it. There is a much higher skill ceiling for prompting than there was for Google-fu.

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

#545

Post by simonw »

SoftTalker wrote: post #535
tkellogg wrote: post #410

Earlier quoted context omitted.

Honestly, this is going to be huge for healthcare. There's an incredible amount of waste due to incumbent tech making interoperability difficult.

> There's an incredible amount of waste due to incumbent tech making interoperability difficult. So the solution to that is to add another layer of complex AI tech on top of it?

Well nothing else we've tried has worked.

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

#546

Post by bigs »

ipaddr wrote: post #512
bigs wrote: post #504

Earlier quoted context omitted.

Try as I might, ChatGPT couldn’t give me working code for a simple admin dash layout in Vue with a sidebar than can minimise. I had to correct it, it would say my apologies and provide new code with a different error. About 10 times in a row it got in a loop of errors and I gave up. Do any of these actually help coding?

Just tried it and it worked. Try this: give me a vue js page. I want a sidebar that minimizes (if triggered). Make simple admin placeholder page.

This was about 6 months ago I think. I’ll happily give it another shot.

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

#547

Post by quantadev »

HappMacDonald wrote: post #506
quantadev wrote: post #326

Earlier quoted context omitted.

Yep. I agree. The "auto-click" thing would be optional. Should be able to turn it on and off. With auto-click off it would just position the mouse and say "click here".

Cluade scans page and decides which button to click before the screen layout is finished. By the time user authorizes the click, layout has shifted and your click lands on malware advertisements.

lol. If any website ever did that to me it would be the last time I ever went to it. Not a big concern for me.

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

#548

Post by simonw »

brigandish wrote: post #514
cryptoz wrote: post #511

Earlier quoted context omitted.

Prompting is a skill you can develop with practice and get better at. Also, some tasks just aren’t going to work well for various reasons. Yes, LLMs can actually help with coding. But it’s not magic. There are limits. And you get better with practice.

Without people providing their prompts, it's impossible to say whether they are skilled or not, and their complaints or claims of "it worked with this prompt" without the output are also not possible to validate. Maybe there's a clue in there as to why these experiences seem so different. I'm glad GPTs don't get frustrated.

I have a personal policy of sharing my prompts as openly as possible. I've shared hundreds at this point - for a bunch of recent examples see https://simonwillison.net/2024/Oct/21/claude-artifacts/ and https://simonwillison.net/tags/ai-assisted-programming/

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

#549

Post by nopinsight »

zeroonetwothree wrote: post #446
nopinsight wrote: post #339

This needs more discussion: Claude using Claude on a computer for coding https://youtu.be/vH2f7cjXjKI?si=Tw7rBPGsavzb-LNo (3 mins) True end-user programming and product manager programming are coming, probably pretty soon. Not the same thing, but Midjourney went from v.1 to v.6 in less than 2 years. If something similar happens, most jobs that could be done remotely will be automatable in a few years.

> If something similar happens, most jobs that could be done remotely will be automatable in a few years. I'd be willing to be a large amount of money this doesn't happen, assuming "most" means >50% and "a few" is <5.

Your semantics above is quite compatible with mine, although I hedged my statement with “a few” which could also mean up to a little over 5, like 6. Also I said “automatable”, not necessarily automated due to legal, political, reputational, or other reasons.

I’m curious to understand your reasoning. What would be some key roadblocks? Hallucinations and reliability issues in most domains will likely be solvable with agentic systems in a few years.

Post reply on HN