Earlier quoted context omitted.
Write tests (plural) first, as in write more than one failing test before making it pass?
Time to look up TDD, my friend.
One of today's lucky 10,000. His mind is about to expand beyond imagination.
Claude 3.7 Sonnet and Claude Code
841–850 of 1001 posts
Re: Claude 3.7 Sonnet and Claude Code
#842Earlier quoted context omitted.
> 225 coding exercises from Exercism Has there been any effort taken to reduce data leakage of this test set? Sounds like these exercises were available on the internet pre-2023, so they'll probably be included in the training data for any modern model, no?
I like to make up my own tests, that way you know it is actually thinking. Tests that require thinking about the physical world are the most revealing. My new favourite is: You have 2 minutes to cool down a cup of coffee to the lowest temp you can. You have two options: 1. Add cold milk immediately, then let it sit for 2 mins. 2. Let it sit for 2 mins, then add cold milk. Which one cools the coffee to the lowest temp…
Obviously you would prepare cold brew the night before.
Re: Claude 3.7 Sonnet and Claude Code
#843Kagi 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…
Thank you to the Kagi team for such fast turn around on new LLMs being accessible via the Assistant! The value of Kagi Assistant has been a no-brainer for me.
[flagged]
Re: Claude 3.7 Sonnet and Claude Code
#844Claude 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
Is aider still relevant vs. Claude Code?
Re: Claude 3.7 Sonnet and Claude Code
#845You 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.
From my predictions:
> Your deep dive into embedded systems will lead you to create a heated keyboard powered by the same batteries as your Milwaukee heated jacket.
While I don't have a Milwaukee heated jacket (I have no idea why it thought this), this feels like a fantastic project idea.
> After years of watching payment technologies evolve, you'll finally embrace cryptocurrency, but only after creating a detailed spreadsheet comparing transaction fees across 17 different payment methods.
I feel seen. I may have created spreadsheets like this for comparing cloud backup options and cars.
From my roast:
> You've spent so much time discussing payment technologies that your credit card probably has a restraining order against you.
This one is completely wrong. They wouldn't do this as they'd lose out on a ton of transaction fees.
Re: Claude 3.7 Sonnet and Claude Code
#846Hi 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.
Did you run the Aider benchmarks to get a comparison of Claude Code vs. Aider?
Re: Claude 3.7 Sonnet and Claude Code
#847Earlier quoted context omitted.
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
What's really the value of a bunch of random anecdotes on HN — but in any case, I've absolutely had the experience of 3.5 falling over on its face when handling a very complex coding task, and o1 pro nailing it perfectly.
Excited to try 3.7 with reasoning more but so far it seems like a modest, welcome upgrade but not any sort of leapfrog past o1 pro.
Re: Claude 3.7 Sonnet and Claude Code
#848Earlier quoted context omitted.
Out of curiosity, what is the answer? From your comment, it seems like the more obvious choice is the incorrect one. EDIT: By the more obvious one, I mean letting it cool and then adding milk. As the temperature difference between the coffee and the surrounding air is higher, the coffee cools down faster. Is this wrong?
That is the correct answer. Also there is a lot of potential nuance, like evaporation or when you take the milk out of the fridge or the specific temperatures of everything, but under realistic settings adding the milk late will get you the colder coffee.
Does the ceramic mug become a factor? As in adding milk first allows the milk to absorb heat that otherwise would have been stored in the mug too quickly and then radiate back into the liquid over time slowing its cooling curve. (I have no idea btw I just enjoy trying to come up with gotchas)
Re: Claude 3.7 Sonnet and Claude Code
#849Earlier quoted context omitted.
TLDR: told it to implement a grid view as an alternative to the existing list view, and specifically told it to DRY the code. What it did? Copy and pasted the list view implementation (definitely not DRY), and tried to make it a grid, and even though it is a grid, it looks terrible ( https://i.imgur.com/fJiSjq4.png ). I don't understand how people use cursor and all that other shit when it cannot follow such simple i…
In any moderately sized codebase it's basically useless indeed. Pretty much all the praise and hype I ever see is from people making todo-list-tier applications and shouting with excitement how this is going to replace all of humanity. Hell, I still have to remind it (Cursor) to not give me fucking React a few messages after I've already told it to not give me React (it's a Vue application with not a single line of R…
I have the opposite experience. I'm incredibly produce with 3.5 in Agent/Composer mode. I wonder if it's something to do with the size of the Vue community (and thus the training data available) versus React.
Re: Claude 3.7 Sonnet and Claude Code
#850Why would they release Claude Code as closed source? Let's hope DeepSeek-r2 delivers, Anthropic is dead. I mean, it's a tool designed to eat itself. Absurd to close source.