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

491–500 of 1001 posts

Re: Claude 3.7 Sonnet and Claude Code

#491

Post by galaxyLogic »

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.

The thing I would like automated is highlighting a function in my code then ask the AI to move it to a new module-file and import that new module.

I would like this to happen easily like hitting a menu or button without having to write an elaborate "prompt" every time.

Is this possible?

Re: Claude 3.7 Sonnet and Claude Code

#492

Post by sylware »

vbezhenar wrote: post #446

So far only o1 pro was breathtaking for me few times. I wrote a kind of complex code for MCU which deals with FRAM and few buffers, juggling bytes around in a complex fashion. I was very not sure in this code, so I spent some time with AI chats asking them to review this code. 4o, o3-mini and claude were more or less useless. They spot basic stuff like this code might be problematic for multi-thread environment, thos…

Is there some truth in the following relationship: o1 -> openai -> microsoft -> github for "training data" ?

Re: Claude 3.7 Sonnet and Claude Code

#493

Post by FeepingCreature »

kadushka wrote: post #427
antirez wrote: post #370

Earlier quoted context omitted.

I guess it's what sometimes it's called "self RAG", that is, the agent looks inside the files how a human would be to find that's relevant.

As opposed to vector search, or…?

To my knowledge these are the options:

1. RAG: A simple model looks at the question, pulls up some associated data into the context and hopes that it helps.

2. Self-RAG: The model "intentionally"/agentically triggers a lookup for some topic. This can be via a traditional RAG or just string search, ie. grep.

3. Full Context: Just jam everything in the context window. The model uses its attention mechanism to pick out the parts it needs. Best but most expensive of the three, especially with repeated queries.

Aider uses kind of a hybrid of 2 and 3: you specify files that go in the context, but Aider also uses Tree-Sitter to get a map of the entire codebase, ie. function headers, class definitions etc., that is provided in full. On that basis, the model can then request additional files to be added to the context.

Re: Claude 3.7 Sonnet and Claude Code

#494

Post by Aeolun »

punkpeye wrote: post #288
airstrike wrote: post #227

Earlier quoted context omitted.

The issue isn't API limits, but web UI limits. We can always get around the web interface's limits by using the claude API directly but then you need to have some other interface...

The API still has limits. Even if you are on the highest tier, you will quickly run into those limits when using coding assistants. The value proposition of Glama is that it combines UI and API. While everyone focuses on either one or the other, I've been splitting my time equally working on both. Glama UI would not win against Anthropic if we were to compare them by the number of features. However, the components th…

> Even if you are on the highest tier, you will quickly run into those limits when using coding assistants.

Even heavy coding sessions never run into Claude limits, and I’m nowhere near the highest tier.

Re: Claude 3.7 Sonnet and Claude Code

#495

Post by tilsammans »

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.

My roasts are savage:

> Your 236-line 'simplified' code example suggests you might need to look up the definition of 'simplified' in a dictionary that's not written in Ruby.

OUCH

> You've spent so much time worrying about Facebook tracking you that you've failed to notice your dental nanobot fantasies are far more concerning to the rest of us.

Heard.

Re: Claude 3.7 Sonnet and Claude Code

#496

Post by Yizahi »

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 predicted Facebook would collapse into a black hole in 2012. The only black hole we found was the one where all your optimism disappeared.

Ouch... :)

PS: This profile check idea is really funny, great job :)

Re: Claude 3.7 Sonnet and Claude Code

#497

Post by 101008 »

stnmtn wrote: post #459
bufferoverflow wrote: post #416

Earlier quoted context omitted.

This test isn't stupid. If it can't count the number of letters in a text, can you rely on it with more important calculations?

You can rely on it for anything that you can validate quickly. And it turns out, there are a lot of problems which are trivial to validate the solution to, but difficult to build the solution.

Coding is not one of those cases or edge cases wouldn't exists

Re: Claude 3.7 Sonnet and Claude Code

#499

Post by cpeterso »

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.

A minor ChatGPT feature I miss with Claude is temporary chats. I use ChatGPT for a lot of random one-off questions and don’t want them filling up my chat history with so many conversations.

Re: Claude 3.7 Sonnet and Claude Code

#500

Post by Yizahi »

nbzso wrote: post #379
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.

This thing is hilarious. :) Roast: - Your comments have more doom predictions than a Y2K convention in December 1999. - You've used 'stochastic parrot' so many times, actual parrots are filing for trademark infringement. - If tech dystopia were an Olympic sport, you'd be bringing home gold medals while explaining how the podium was designed by committee and the medal contains surveillance chips.

> You've used 'stochastic parrot' so many times, actual parrots are filing for trademark infringement.

Ahahaha:) This line wins:)

Post reply on HN