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

691–700 of 1001 posts

Re: Claude 3.7 Sonnet and Claude Code

#691

Post by jcheng »

simonw wrote: post #519
marlott wrote: post #304

Earlier quoted context omitted.

Interesting - can you elaborate a little on what you mean by agentic search here?

Since the Claude Code docs suggest installing Ripgrep, my guess is that they mean that Claude Code often runs searches to find snippets to improve in the context. I would argue that this is still RAG. There's a common misconception (or at least I think it's a misconception) that RAG only counts if you used vector search - I like to expand the definition of RAG to include non-vector search (like Ripgrep in this case),…

I agree that retrieval can take many forms besides vector search, but do we really want to call it RAG if the model is directing the search using a tool call? That like an important distinction to me and the name "agentic search" makes a lot more sense IMHO.

Re: Claude 3.7 Sonnet and Claude Code

#692

Post by tomduncalf »

neal_ wrote: post #638
keithwhor wrote: post #161

Earlier quoted context omitted.

I think an argument could be reasonably made that the app layer is the only moat. It’s more likely Anthropic eventually has to acquire Cursor to cement a position here than they out-compete it. Where, why, what brand and what product customers swipe their credit cards for matters — a lot.

Cursor has no models, they dont even have an editor its just vscode

They do actually have custom models for autocomplete (which requires very low latency) and applying edits from the LLM (which turns out to require another LLM step, as they can’t reliably output perfect diffs)

Re: Claude 3.7 Sonnet and Claude Code

#693

Post by girvo »

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 asked about building a homebrew computer in 2013, and we're still waiting for the 'Show HN' post. Moore's Law has changed less than your project timeline.

> Your journey from PHP to OCaml suggests you enjoy pain, just in increasingly sophisticated forms.

> You seem to spend so much time worrying about NSA surveillance that you probably encrypt your grocery lists. The NSA agent assigned to you is bored to tears.

Hahaha these are excellent, though it really latched on to the homebrew PC stuff I was into back in 2013

Re: Claude 3.7 Sonnet and Claude Code

#694

Post by girvo »

srhtftw wrote: post #671
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 critiquing nil values in Lua tables that you could have rewritten the entire language by now. Maybe in 2025? * Your perfect tech stack exists only in your comments - a beautiful utopia where everything is type-safe, reliable, and nobody is ever on-call. * You evaluate programming languages the way wine critics evaluate vintages: 'Ah yes, Effect-ts 2023, a sophisticated choice with notes of…

Okay that last one is phenomenal hahaha

Re: Claude 3.7 Sonnet and Claude Code

#695

Post by girvo »

satvikpendem wrote: post #625
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.

Looks like it's really only using the most recent comments, rather than looking at all of them across the lifetime of the account.

Mine went wayyy back to 2013, so I'm not sure its recent comments per se.

Re: Claude 3.7 Sonnet and Claude Code

#696

Post by fragmede »

sejje wrote: post #647
doctoboggan wrote: post #636

Earlier quoted context omitted.

I like Aider but I've turned off auto-commit. I just can't seem to let the AI actually commit code for me. Do you regularly let Aider commit for you? How much do you review the code written by it?

I don't let it auto commit, either. I don't like committing in a broken state, and the llm breaks things plenty often.

The beauty of git is that local commits don't get seen by anybody until you push. so you can commit early and commit often, since no one else is gonna see it, which gets you checkpoints before, during, and after you dive into making a big breaking change in the code. once you've got something you like, then you can edit, squash, and reorder the local commits and clean them up for consumption by the general public.

But to each their own!

Re: Claude 3.7 Sonnet and Claude Code

#697

Post by pzo »

danw1979 wrote: post #470
throw83288 wrote: post #452

Earlier quoted context omitted.

Serious question: What advice would you give to a Computer Science student in light of these tools?

Serious answer: learn to code. You still need to know what good code looks like to use these tools. If you go forward in your career trusting the output of LLMs without the skills to evaluate the correctness, style, functionality of that code then you will have problems. People still write low level machine code today, despite compilers having existed for 70+ (?) years. We'll always need full-stack humans who underst…

I will give a little more pessimistic answer. If someone is right now studying CS then probably have expectation that can work with this profession for 30-40 years until retirement and this profession will still pay much more than average salary for most of devs anywhere (instead only of elite devs or those in US) and easily to find such job or easily switch employer.

I think the best period of Software Devs will be gone in few years. Knowing how how to code and fix things will be important still but more important to be also Jack-of-Many-Trades to provide more value: know a little about SEO, have a good taste of design and be able to tweak simple design, good taste how to organise code, better soft skills and managing or educating less tech-savvy stuff.

Another option is to specialise in some currently difficult subfield: robotics, ML, CUDA, rust and try to be this elite dev with expectation would have to move to SV or any such tech hub.

Best general recommendation I would give right now (especially for someone who is not from US) to someone who is currently studying is to use that a lot of time you have right now with not much responsibility to make some product that can provide you semi-passive income on a monthly basis ($5k-$10k) to drag yourself out of this rat race. Even if you not succeed or revenue stream will run out eventually you will learn those other skills that will be more important later if wanna be employed (SEO, code & design taste, marketing, soft skills).

Because most likely this window of opportunity might be only for the next few years in similar way when the best window for Mobile Apps was first ~2 years when App Store started

Re: Claude 3.7 Sonnet and Claude Code

#698

Post by khafra »

mikae1 wrote: post #686
anotherpaulg wrote: post #580

Earlier quoted context omitted.

Using up to 32k thinking tokens, Sonnet 3.7 set SOTA with a 64.9% score. 65% Sonnet 3.7, 32k thinking 64% R1+Sonnet 3.5 62% o1 high 60% Sonnet 3.7, no thinking 60% o3-mini high 57% R1 52% Sonnet 3.5

It's clear that progress is incremental at this point. At the same time Anthropic and OpenAI are bleeding money. It's unclear to me how they'll shift to making money while providing almost no enhanced value.

Yudkowsky just mentioned that even if LLM progress stopped right here, right now, there are enough fundamental economic changes to provide us a really weird decade. Even with no moat, if the labs are in any way placed to capture a little of the value they've created, they could make high multiples of their investors' money.

Re: Claude 3.7 Sonnet and Claude Code

#699

Post by DandyDev »

0xcb0 wrote: post #409

I can just say that this is awesome. I just did spend 10$ and a handful of querys to init up a app idea I had in a while. The basic idea is working, it handled everything for me. From setting up the node environment. Creating the directories, files, patching the files, running code, handling errors, patching again. From time to time it fails to detect its own faults. But when I pinpoint it, it get it most of the time…

What tool/editor/IDE did you use to do this?

Re: Claude 3.7 Sonnet and Claude Code

#700

Post by vessenes »

anotherpaulg wrote: post #580
anotherpaulg wrote: post #331

Claude 3.7 Sonnet scored 60.4% on the aider polyglot leaderboard [0], WITHOUT USING THINKING. Tied for 3rd place with o3-mini-high. Sonnet 3.7 has the highest non-thinking score, taking that title from Sonnet 3.5. Aider 0.75.0 is out with support for 3.7 Sonnet [1]. Thinking support and thinking benchmark results coming soon. [0] https://aider.chat/docs/leaderboards/ [1] https://aider.chat/HISTORY.html#aider-v0750

Using up to 32k thinking tokens, Sonnet 3.7 set SOTA with a 64.9% score. 65% Sonnet 3.7, 32k thinking 64% R1+Sonnet 3.5 62% o1 high 60% Sonnet 3.7, no thinking 60% o3-mini high 57% R1 52% Sonnet 3.5

Paul, I saw in the notes that using claude with thinking mode requires yml config updates -- any pointers here? I was parsing some commits, and I couldn't tell if you only added architect support through openrouter. Thanks!
Post reply on HN