Recommendations you can check.
by Anthropic
Who uses, recommends or left Claude Code, in their own words: each a verbatim quote with a link to where it was said.
12 people
Three out of three one-shot debugging hits with no help is extremely impressive.
Post describing Claude Code one-shotting three low-level cryptography bugs in his ML-DSA implementation; discloses Anthropic gave him free Claude Max
2025-11-01·words.filippo.io ↗
these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code.
2026-04-09·x.com ↗
Claude Code (CC) emerged as the first convincing demonstration of what an LLM Agent looks like - something that in a loopy way strings together tool use and reasoning for extended problem solving.
His year-in-review of the LLM 'paradigm changes' of 2025.
2025-12-19·karpathy.bearblog.dev ↗
TL;DR: Ghostty + Claude Code + minimal tooling = maximum productivity.
The summary line of his workflow post, naming the stack he settled on.
2025-08-25·steipete.me ↗
I really recommend trying it rather than assuming. There's no learning curve, you just install Claude Code and run it in your repo and ask it for things.
In the Hacker News thread on Cloudflare's Claude-generated commits, replying to a skeptic; he wrote the prompts behind that code.
2025-06-07·news.ycombinator.com ↗
Like seemingly everyone else at the end of last year, I began messing around with Claude Code, and have since made a small handful of apps that I really do use all the time.
His annual productivity post, running down the software he still uses, what he dropped, and the LLM wiki he built. The post carries his standing disclosure that his fiancé works at Anthropic.
2026-08-19·platformer.news ↗
When writing code, I'm mostly in Xcode, often in concert with Prompt and, lately, Claude Code.
His written "Uses This" interview, covering his development, podcasting and home-network setup.
2026-06-30·usesthis.com ↗
I have to admit that I still primarily alternate between Codex and Claude Code as my daily drivers, for now
A walkthrough of running coding agents against local open-weight models; he names the models and tools he uses.
2026-06-27·magazine.sebastianraschka.com ↗
It's just tabs for my sites, all on a VPS, synced with my iPhone via @TermiusHQ (unaffiliated) and usually with Claude Code open to fix or build new things
Describing what his laptop and phone screens look like all day.
2026-05-22·levels.io ↗
With Claude, I've built a host of software like this. Mostly small tools for myself — programs that instantly append copy buffers to text files (I keep a running file of nice things people write to me called notapieceofshit.txt) or quickly perform live currency conversions.
An essay on a year of building his own small software with Claude Code. His essay index dates it March 2026 with no day given.
2026-03-01·craigmod.com ↗
My daily drivers now include Amp, Cursor, and Claude Code. I still enjoy notebooks, but only for data analysis, machine learning, or other exploratory workflows where the iterative, visual nature of notebooks shines.
'Why I Stopped Using nbdev' — on how AI coding tools changed which development tools he picks.
2026-01-18·hamel.dev ↗
For all intents and purposes, here’s what I do: I predominently use Claude Code with the cheaper Max subscription for $100 a month
Post laying out his agentic-coding practices and tool choices.
2025-06-12·lucumr.pocoo.org ↗
I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc.
Complaining that the coding agent reads only CLAUDE.md rather than the shared AGENTS.md convention.
2026-08-25·x.com ↗
I used to love Claude Code, these days I can’t stand it anymore
A hand-written guide to working with coding agents; here he explains why he moved off Claude Code to Codex.
2025-10-14·steipete.me ↗
Every entry is a verbatim quote and a link to the public post it came from. Nothing is paraphrased. If it is not on record somewhere public, it is not here.
The verdict is what they actually said: loved and liked are explicit; recommended means they told others to get it; uses means they only say they use it; read is a book on their public shelf with no verdict; mixed and disliked are kept too.
A dashed affiliate link, sponsored or their own label means the post disclosed a relationship. It is shown, never hidden.
The shading behind a date shows how dated a recommendation is for its kind of thing.
The shading behind a date shows how dated a recommendation is, for its kind of thing. Fully green is recent. It drains a quarter at a time as the post gets older, and is empty once it reads as dated.
What counts as old depends on the thing. A laptop praised four years ago has been replaced twice; a book loved twenty years ago is probably still loved. The shading is gone after about:
Stripes mean the post carries no date and the date shown is an estimate. No date at all, no shading.