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

361–370 of 1001 posts

Re: Claude 3.7 Sonnet and Claude Code

#361

Post by davidbarker »

gwd wrote: post #359
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.

Just started playing with the command-line tool. First reaction (after using it for 5 minutes): I've been using `aider` as a daily driver, with Claude 3.5, for a while now. One of the things I appreciate about aider is that it tells you how much each query cost, and what your total cost is this session. This makes it low-key easy to keep tabs on the cost of what I'm doing. Any chance you could add that to claude-code…

If you do `/cost` it will tell you how much you've spent during that session so far.

Re: Claude 3.7 Sonnet and Claude Code

#362

Post by eschluntz »

gwd wrote: post #359
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.

Just started playing with the command-line tool. First reaction (after using it for 5 minutes): I've been using `aider` as a daily driver, with Claude 3.5, for a while now. One of the things I appreciate about aider is that it tells you how much each query cost, and what your total cost is this session. This makes it low-key easy to keep tabs on the cost of what I'm doing. Any chance you could add that to claude-code…

hi! You can do /cost at any time to see what the current session has cost

Re: Claude 3.7 Sonnet and Claude Code

#363

Post by manmal »

Squarex wrote: post #345
freediver wrote: post #251

Kagi LLM benchmark updated with general purpose and thinking mode for Sonnet 3.7. https://help.kagi.com/kagi/ai/llm-benchmark.html Appears to be second most capable general purpose LLM we tried (second to gemini 2.0 pro, in front of gpt-4o). Less impressive in thinking mode, about at the same level as o1-mini and o3-mini (with 8192 token thinking budget). Overall a very nice update, you get higher quality and higher…

I'm surprised that Gemini 2.0 is first now. I remember that Google models were under performing on kagi benchmarks.

Gemini 2 is really good, and insanely fast.

Re: Claude 3.7 Sonnet and Claude Code

#364

Post by LouisSayers »

TriangleEdge wrote: post #94

This AI race is happening so fast. Seems like it to me anyway. As a software developer/engineer I am worried about my job prospects.. time will tell. I am wondering what will happen to the west coast housing bubbles once software engineers lose their high price tags. I guess the next wave of knowledge workers will move in and take their place?

I'm not too concerned short to medium term. I feel there are just too many edge cases and nuances that are going to be missed by AI systems.

For example, systems don't always work in the way they're documented to. How is an AI going to differentiate cases where there's a bug in a service vs a bug in its own code? How will an AI even learn that the bug exists in the first place? How will an AI differentiate between someone reporting a bug and a hacker attempting to break into a system?

The world is a complex place and without ACTUAL artificial intelligence we're going to need people to at least guide AI in these tricky situations.

My advice would be to get familiar with using AI and new AI tools and how they fit into our usual workflows.

Others may disagree, but I don't think software engineers (at least ones the good ones) are going anywhere.

Re: Claude 3.7 Sonnet and Claude Code

#365

Post by pertymcpert »

thefourthchime wrote: post #335
freediver wrote: post #251

Kagi LLM benchmark updated with general purpose and thinking mode for Sonnet 3.7. https://help.kagi.com/kagi/ai/llm-benchmark.html Appears to be second most capable general purpose LLM we tried (second to gemini 2.0 pro, in front of gpt-4o). Less impressive in thinking mode, about at the same level as o1-mini and o3-mini (with 8192 token thinking budget). Overall a very nice update, you get higher quality and higher…

Nice, but where is Grok?

Perhaps they're waiting for the Grok API to be public?

Re: Claude 3.7 Sonnet and Claude Code

#366

Post by airstrike »

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…

Ok, but that's not the issue the parent was mentioning. I've never hit API limits but, like the original comment mentioned, I too constantly hit the web interface limits particularly when discussing relatively large modules.

Re: Claude 3.7 Sonnet and Claude Code

#367

Post by agys »

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 more time optimizing DOM manipulation for ASCII art than most people spend deciding what to watch on Netflix in their entire lives.”

Ouch… :)

Re: Claude 3.7 Sonnet and Claude Code

#368

Post by k8sToGo »

slantedview wrote: post #252

As a Claude Pro user, one of the biggest problems I have with day to day use of Sonnet is running out of tokens, and having to wait several hours. Would this new deep thinking capability just hit this problem faster?

Have you tried just using the API and pay as you go?

Re: Claude 3.7 Sonnet and Claude Code

#369

Post by aquariusDue »

CharlesW wrote: post #316
keithwhor wrote: post #248

Earlier quoted context omitted.

(1) That's a big if. It requires building a team specialized in delivering what Cursor has already delivered which is no small task. There are probably only a handful of engineers on the planet that have or can be incentivized to develop the product intuition the Cursor founders have developed in the market already. And even then; I'm an aspiring engineer / PM at Anthropic. Why would I choose to spend all of my creat…

> It requires building a team specialized in delivering what Cursor has already delivered which is no small task. There are several AIDEs out there, and based on working with Cursor, VS Code, and Windsurf there doesn't seem to be much of a difference (although I like Windsurf best). What moat does Cursor have?

Just chiming in to say that AIDEs (Artificial Intelligence Development Environments, I suppose) is such a good term for these new tools imo.

It's one thing to retrofit LLMs into existing tools but I'm more curious how this new space will develop as time goes on. Already stuff like the Warp terminal is pretty useful in day to day use.

Who knows, maybe this time next year we'll see more people programming by voice input instead of typing. Something akin to Talon Voice supercharged by a local LLM hopefully.

Re: Claude 3.7 Sonnet and Claude Code

#370

Post by antirez »

marlott wrote: post #304
bcherny wrote: post #264

Earlier quoted context omitted.

Right -- Claude Code doesn't use RAG currently. In our testing we found that agentic search out-performed RAG for the kinds of things people use Code for.

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

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.
Post reply on HN