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

Claude 3.7 Sonnet and Claude Code

anthropic.com

Post reply on HN
Print view View original

721–730 of 1001 posts

Re: Claude 3.7 Sonnet and Claude Code

#721

Post by indeyets »

rudedogg wrote: post #680
Sterling9x wrote: post #675

Earlier quoted context omitted.

That's a file context problem because you use cursor or cline or some other crap context maker. Try Clood. Unless "anthropic high usage" which I just watch the incident reports I one shot features regularly. At a high skill level. Not front end. Back end c# in a small but great framework that has poor documentation. Not just endpoints but full on task queues. So really, it's a context problem. You're just not laser f…

Wtf is “clood”?

probably this https://github.com/atomicwrite/Clood

Re: Claude 3.7 Sonnet and Claude Code

#722

Post by antouank »

bcherny wrote: post #91

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

Hi there. There are lots of phrases/patterns that Claude always uses when writing and it was very frustrating with 3.5. I can see with 3.7 those persist. Is there any way for me to contact you and show those so you can hopefully address them?

Re: Claude 3.7 Sonnet and Claude Code

#725

Post by throwaway454647 »

babyshake wrote: post #190
bcherny wrote: post #91

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

One thing I would love to have fixed - I type in a prompt, the model produces 90% or even 100% of the answer, and then shows an error that the system is at capacity and can't produce an answer. And then the response that has already been provided is removed! Please just make it where I can still have access to the response that has been provided, even if it is incomplete.

I'll be publishing a Firefox extension as a temporary fix, will post it here. (I don't use Chrome.)

Re: Claude 3.7 Sonnet and Claude Code

#726

Post by OsrsNeedsf2P »

vessenes wrote: post #92
phillipcarter wrote: post #78

Earlier quoted context omitted.

Neither a statement for or against Grok or Anthropic: I've now just taken to seeing benchmarks as pretty lines or bars on a chart that are in no way reflective of actual ability for my use cases. Claude has consistently scored lower on some benchmarks for me, but when I use it in a real-world codebase, it's consistently been the only one that doesn't veer off course or "feel wrong". The others do. I can't quantify it…

O1 pro is excellent at figuring out complex stuff that Claude misses. It’s my go to mid level debug assistant when Claude spins

I have never, in frontend, backend, or Android, had O1 pro solve a problem Claude 3.5 could not. I've probably tried it close to 20 times now as well

Re: Claude 3.7 Sonnet and Claude Code

#727

Post by yalok »

hubraumhugo wrote: post #131

You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.

> You've spent so much time optimizing ML models that your own brain now refuses to process any thought that could be represented more efficiently with fewer neurons.

Re: Claude 3.7 Sonnet and Claude Code

#728

Post by Maxion »

fixprix wrote: post #711
wokwokwok wrote: post #665

Earlier quoted context omitted.

"no lines of code directly written, just directing the AI" /skeptical face. Without fail, every. single. person. I've met who says that, actually means "except for the code that I write", or "except for how I link the code it build together by hand". If you are 50kloc in to a large complex project that you have literally written none of, and have, eg. used cursor to generate the code without any assistance... well, y…

If you know how to architect code well, you can guide the AI to create smaller more targeted modules. That way as you 'write code with AI', you give it a targeted subset of the files to edit on each prompt. In a way the AI becomes the dev and you become the code reviewer. Often as the AI is writing the code, you're thinking about the next step.

It's not like you go to claude and say "Grug now use AI, Grug say AI make app OR GRUG HIT AI WITH HAMMER!" and expect 50kloc of code to appear.

You do it one step at a time, similary to how you would structure good tickets (often even smaller).

AI often still makes shit, but you do get somewhere a whole heap load of time faster.

Re: Claude 3.7 Sonnet and Claude Code

#729

Post by AlfeG »

Ahha, recently my daugher come to me with 3rd grade math problem. "Without rearranging the digits 1 2 3 4 5, insert mathematical operation signs and, if necessary, parentheses between them so that the resulting expression equals 40 and 80. The key is that you can combine digits (like 12+3/45) but you cannot change their order from the original sequence 1,2,3,4,5"

Grok3, Claude, Deepseek, Qwen all failed to solve this problem. Resulting in some very very wrong solutions. While Grok3 were admit it fail and don't provide answers all other AI's are provided just plain wrong answers, like `12 * 5 = 80`

ChatGPT were able to solve for 40, but not able to 80. YandexGPT solved those correctly (maybe it were trained on same Math books)

Just checked Grok3 few more times. It were able to solve correctly for 80.

Re: Claude 3.7 Sonnet and Claude Code

#730

Post by Madmallard »

Is it actually good at solving complex code or is it just garbage and people are lying about it as usual?

In my experience EXTENSIVELY using claude 3.5 sonnet you basically have to do everything complex or you're just introducing massive amounts of slop code into your code base that while functional is nowhere near good. And for anything actually complex like requires a lot of context to make a decision and has to be useful to multiple different parts, it's just hopelessly bad.

Post reply on HN