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

511–520 of 758 posts

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

#511

Post by cryptoz »

bigs wrote: post #504
faizshah wrote: post #501

Earlier quoted context omitted.

Anecdotally but I still get significantly better results from ChatGPT than claude for coding. Claude is way less controllable it is difficult to get it to do exactly what I want. ChatGPT is way easier to control in terms of asking for specific changes. Not sure why that is maybe the chain of thought and instruction tuning dataset has made theirs a lot better for interactive use.

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?

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.

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

#512

Post by ipaddr »

bigs wrote: post #504
faizshah wrote: post #501

Earlier quoted context omitted.

Anecdotally but I still get significantly better results from ChatGPT than claude for coding. Claude is way less controllable it is difficult to get it to do exactly what I want. ChatGPT is way easier to control in terms of asking for specific changes. Not sure why that is maybe the chain of thought and instruction tuning dataset has made theirs a lot better for interactive use.

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.

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

#513

Post by simonw »

bigs wrote: post #504
faizshah wrote: post #501

Earlier quoted context omitted.

Anecdotally but I still get significantly better results from ChatGPT than claude for coding. Claude is way less controllable it is difficult to get it to do exactly what I want. ChatGPT is way easier to control in terms of asking for specific changes. Not sure why that is maybe the chain of thought and instruction tuning dataset has made theirs a lot better for interactive use.

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?

Give it one or two examples of what you want. Don't expect these things to perfectly solve every problem - they're transformation machines, so they can do pretty much anything if you figure out the right input.

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

#514

Post by brigandish »

cryptoz wrote: post #511
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?

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.

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

#515

Post by aledalgrande »

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 query in Access. You can imagine how excited he was. Was a fun little project and pretty hilarious to see the cursor moving fast AF around the screen like it was possessed. PS: you could screw up the script run pretty easily by bumping into the mouse of that pc.

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

#516

Post by simonw »

runako wrote: post #510
mathnmusic wrote: post #473

Earlier quoted context omitted.

It does not have access to the Excel app. You may be able to generate the .xlsx file using python libraries but you would need to run the python code on your own. ChatGPT can run generated code, which is probably why it works there.

I don't expect it to have the Excel app, I expect it to run the code it is capable of generating. This is what I mean by their strategy being a jumble. Claude can do the hard part of figuring out what code to write and writing it, but then refuses to do the easier part of executing the code.

The Claude web UI cannot generate binary files, it's (currently) restricted to plain text.

If you want binary files you'd be better off with ChatGPT with Code Interpreter mode, which can run Python code that generates binary content.

Or ask Claude to write you Python code that generates Excel files and then copy and paste that onto your own computer and run it yourself.

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

#517

Post by mewpmewp2 »

falcor84 wrote: post #496
mewpmewp2 wrote: post #464

Earlier quoted context omitted.

True, 2FA and all these little details that exist now have made this automation quite insanely complicated. It is of course necessary that we have 2FA etc, but there is huge potential in solving this I believe.

From a security standpoint, what's considered the "proper" way of assigning a bot access based on a person's 2FA? Would that be some sort of limited scope expiring token like GitHub's fine-grained personal access tokens?

I don't know, I feel like it has to be some sort of near field identity proof. E.g. as long as you are wearing a piece of equipment to a physical computer near you can run all those automations for you, or similar. I haven't fully thought what the best solution could be or whether someone is already working on it, but I feel like there has to be something like that, which would allow you better UX in terms of access, but security at the same time.

So maybe like an automated ubikey that you can opt in to a nearby computer to have all the access. Especially if working from home, you can set it at a state where if you are in 15m radius of your laptop it is able to sign all access.

Because right now, considering amount of tools and everything I use and with single sign on, VPN, Okta, etc, and how slow they seem to be, it's extremely frustrating process constantly logging in to everywhere, and it's almost like it makes me procrastinate my work, because I can't be bothered. Everything about those weird little things is absolutely terrible experience, including things like cookie banners as well.

And it is ridiculous, because I'm working from home, but frustratingly high amount of time is spent on this bs.

A bluetooth wearable or similar to prove that I'm nearby essentially, to me that seems like it could alleviate a lot of safety concerns, while providing amazing dev/ux.

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

#518

Post by javajosh »

quantadev wrote: post #340
javajosh wrote: post #309

Earlier quoted context omitted.

AI and new tools have broken the system. The tools send you email saying things like "X corp is interested in you!" and you send a resume, and you don't hear back. Nothing, not even a rejection. Eventually you stop believing them, understanding it for the marketing spam that it is. Direct submissions are better, but only slightly. Recruiters are much better, in general, since they have a relationship with a real pers…

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 that they actually saw your application, you know things are bad.

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

#519

Post by runako »

simonw wrote: post #516
runako wrote: post #510

Earlier quoted context omitted.

I don't expect it to have the Excel app, I expect it to run the code it is capable of generating. This is what I mean by their strategy being a jumble. Claude can do the hard part of figuring out what code to write and writing it, but then refuses to do the easier part of executing the code.

The Claude web UI cannot generate binary files, it's (currently) restricted to plain text. If you want binary files you'd be better off with ChatGPT with Code Interpreter mode, which can run Python code that generates binary content. Or ask Claude to write you Python code that generates Excel files and then copy and paste that onto your own computer and run it yourself.

> you'd be better off with ChatGPT with Code Interpreter mode

Yes, this is what I am saying. Why go to the trouble to build something as capable as Claude and then hamstring it from being as useful as ChatGPT? I have no doubt that Claude could be more useful if the Anthropic team would let it shine.

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

#520

Post by runako »

tucnak wrote: post #455
runako wrote: post #385

Earlier quoted context omitted.

I asked it to generate a very basic Excel file. It generated text as Markdown. I reiterated that I want an Excel file with formulae and it provided this as part of its response: ---- No, I am not able to generate or create an actual Excel file. As an AI language model, I don't have the capability to create, upload, or send files of any kind, including Excel spreadsheets. ----

This is claude.ai or console.anthropic.com?

I believe Claude.ai, but I run as a Safari Web app because Anthropic doesn't ship a native app for MacOS (which I would prefer).
Post reply on HN