It's smarter, but it also feels more aggressive than 3.5. I'm finding I need to tell it not to do superfluous things more often
Claude 3.7 Sonnet and Claude Code
891–900 of 1001 posts
Re: Claude 3.7 Sonnet and Claude Code
#892Earlier quoted context omitted.
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…
I have another easy one which thinking models get wrong: "Anhentafel numbers start with you as 1. To find the Ahhentafel number of someone's father, double it. To find the Ahnentafel number of someone's mother, double it and add one. Men pass on X chromosome DNA to their daughters, but none to their sons. Women pass on X chromosome DNA to both their sons and daughters. List the Ahnentafel numbers of the closest 20 an…
Yeah I wouldn't call this easy...
Re: Claude 3.7 Sonnet and Claude Code
#893Re: Claude 3.7 Sonnet and Claude Code
#894Earlier 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.
Time to actually read Test-Driven Development By Example, my friend. Or if you can't stomach reading a whole book, read this: https://tidyfirst.substack.com/p/canon-tdd
TL;DR - If you're writing more than one failing test at a time, you are not doing Test-Driven Development.
Re: Claude 3.7 Sonnet and Claude Code
#895Anecdotal cost impact- After toying with Claude Code for the afternoon, my Anthropic spend just went from $20/mo to $10/day. Still worth it, but that’s a big jump.
So it’s an order of magnitude more effective?
Perhaps a magnitude more effective than copy/paste, perhaps not. But do I get more than $300/month of value from it, per developer? Almost certainly.
The bottleneck was already checking the work for correctness and building my own trust / familiarity with new code. So it's made that problem slightly more pronounced, as it generates more code faster, with more surface area to debug when many new changes arrive at once.
Re: Claude 3.7 Sonnet and Claude Code
#896Earlier quoted context omitted.
What do you even do then as a student? I've asked this dozens of times with zero practical answers at all. Frankly I've become entirely numb to it all.
I'm sure lots of potential students / bootcampers are now not going into programming (or if they are, the smart ones try to go into niches like A.I and skip web/backend/android altogether). This will work against the numbers of jobs being reduced by A.I. It will take a few years though to play out , but at some point we will see smaller amounts of people trying to get into the field and applying for jobs, certainly f…
When I say 10 years I say that I've probably wanted to work in this field since maybe 10. Computing is my autistic hyperfixation. This is why I'm so frustrated.
Re: Claude 3.7 Sonnet and Claude Code
#897I got this working with my LLM tool (new plugin version: llm-anthropic 0.14) and figured out a bunch of things about the model in the process. My detailed notes are here: https://simonwillison.net/2025/Feb/25/llm-anthropic-014/
One of the most exciting new capabilities is that this model has a 120,000 token output limit - up from just 8,000 for the previous Claude 3.5 Sonnet model and way higher than any other model in the space.
It seems to be able to use that output limit effectively. Here's my longest result so far, though it did take 27 minutes to finish! https://gist.github.com/simonw/854474b050b630144beebf06ec4a2...
Re: Claude 3.7 Sonnet and Claude Code
#898I got this working with my LLM tool (new plugin version: llm-anthropic 0.14) and figured out a bunch of things about the model in the process. My detailed notes are here: https://simonwillison.net/2025/Feb/25/llm-anthropic-014/ One of the most exciting new capabilities is that this model has a 120,000 token output limit - up from just 8,000 for the previous Claude 3.5 Sonnet model and way higher than any other model…
How much did it cost?
Re: Claude 3.7 Sonnet and Claude Code
#899Earlier quoted context omitted.
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.
It's an echo chamber.
It is - what? - a fifth anniversary of "the world will be a completely different place in 6 months due to AI advancement"?
"Sam Altman believes AI will change the world" - of course he does, what else is he supposed to say?
Re: Claude 3.7 Sonnet and Claude Code
#900I got this working with my LLM tool (new plugin version: llm-anthropic 0.14) and figured out a bunch of things about the model in the process. My detailed notes are here: https://simonwillison.net/2025/Feb/25/llm-anthropic-014/ One of the most exciting new capabilities is that this model has a 120,000 token output limit - up from just 8,000 for the previous Claude 3.5 Sonnet model and way higher than any other model…
No shade against Sonnet 3.7, but I don't think it's accurate to say way higher than any other model in the space. o1 and o3-mini go up to 100,000 output tokens.