Wonder what the context window is for Claude Code for internal users
How Anthropic teams use Claude Code
31–40 of 248 posts
Re: How Anthropic teams use Claude Code
#32Claude Code works well for lots of things; for example yesterday I asked it to switch weather APIs backing a weather site and it came very close to one-shotting the whole thing even though the APIs were quite different. I use it at home via the $20/m subscription and am piloting it at work via AWS Bedrock. When used with Bedrock APIs, at the end of every session it shows you the dollar amount spent which is a bit dis…
once upon a time - engineers often had to concern themselves with datacenter bills, cloud bills, and eventually SaaS bills. We'll probably have 5-10 years of being concerned about AI bills before the AI expense is trivial compared to the human time.
AI bills are already trivial compared to human time. I pay for claude max, all I need to do is save an hour a month and I will be breaking even.
Re: How Anthropic teams use Claude Code
#33Earlier quoted context omitted.
once upon a time - engineers often had to concern themselves with datacenter bills, cloud bills, and eventually SaaS bills. We'll probably have 5-10 years of being concerned about AI bills before the AI expense is trivial compared to the human time.
You will start seriously worrying about coding AI bills within 6 months
Why is that?
Re: How Anthropic teams use Claude Code
#34Wouldn't it be a bit unusual if that wasn't true? We build our coding agent...with our coding agent... feeling like this is table steaks.
I bet your dog really loves you if steak is your idea of dogfooding ;)
Re: How Anthropic teams use Claude Code
#35It's funny since Anthropic asked their job candidates not to use AI [0]. I know it's not the same as actually working at Anthropic already, but I just thought it was funny.
[0] https://fortune.com/2025/02/04/anthropic-tells-job-candidate...
Re: How Anthropic teams use Claude Code
#36> Create self-sufficient loops
>
> Set up Claude to verify its own work by running builds, tests, and lints automatically.
I’ve got much better at using Claude.md and plan files, etc., but it still goes off the rails so quickly when I try to get it to follow a normal TDD test/edit/build/commit workflow. It will report success, and then the unit tests will fail or the working copy is dirty or there are build errors, etc. An LLM may be great for figuring out what code to write and what weird tool incantation to run to debug something, but I am fed up enough I want to write my own agent, because all I want is a switch-statement state machine to manage workflow.
Re: How Anthropic teams use Claude Code
#37It's funny since Anthropic asked their job candidates not to use AI [0]. I know it's not the same as actually working at Anthropic already, but I just thought it was funny. [0] https://fortune.com/2025/02/04/anthropic-tells-job-candidate...
They want cracked developers and sell the slop generator to script kiddies.
Re: How Anthropic teams use Claude Code
#38I used to say that the last 10% of software takes 90% of the effort. All the 70 percents and 80 percents in that article reminded me of that.
Re: How Anthropic teams use Claude Code
#39It's funny since Anthropic asked their job candidates not to use AI [0]. I know it's not the same as actually working at Anthropic already, but I just thought it was funny. [0] https://fortune.com/2025/02/04/anthropic-tells-job-candidate...
Anthropic are trailblazers and this will be everywhere soon. It happened to me tonight with a different company. "We use AI to do our actual work, but please don't use AI for this coding challenge."
Re: How Anthropic teams use Claude Code
#40So this style of articles is the future? Pages of unconnected bullet points that mention the word "Claude" at least 100 times. No real information and nothing to remember.