I regret migrating to Codeberg(xn--gckvb8fzb.com)

448 points by boramalper 3 months ago | 358 comments

Personal blog post explaining the author's regret about moving projects to Codeberg after its new terms restricting which projects are welcome.

Snorting the AGI with Claude Code(kadekillary.work)

290 points by beigebrucewayne 1 year ago | 183 comments

Making a game on a custom bytecode VM in 7 days and 3kB(laurent.le-brun.eu)

71 points by laurentlb 10 months ago | 11 comments

The TEMU-Fication of Software, Digital Goods and Services(xn--gckvb8fzb.com)

152 points by surprisetalk 2 months ago | 103 comments

Making Rust supply chain attacks harder with Cackle(davidlattimore.github.io)

169 points by djoldman 3 years ago | 71 comments

The Cables That Connect the World(xn--gckvb8fzb.com)

42 points by surprisetalk 1 month ago | 8 comments

Claude Code can debug low-level cryptography(words.filippo.io)

446 points by Bogdanp 11 months ago | 199 comments

Filippo Valsorda's blog post on using Claude Code to debug his new Go implementation of the ML-DSA post-quantum signature algorithm.

Claude Code: Best practices for agentic coding(anthropic.com)

549 points by sqs 1 year ago | 232 comments

Anthropic engineering blog post sharing tips and best practices for using Claude Code, a command-line tool for agentic coding, across codebases and languages.

A guide to local coding models(aiforswes.com)

551 points by mpweiher 10 months ago | 304 comments

A Substack newsletter post guiding software engineers on running local coding models as an alternative to paying for Claude Code, covering tooling and setup steps.

The highest quality codebase(gricha.dev)

603 points by Gricha 10 months ago | 371 comments

Blog post by Greg Pstrucha describing an experiment in which Claude repeatedly reworked an app's codebase to make it the "highest quality", and what happened.

My finetuned models beat OpenAI's GPT-4(mlops.systems)

376 points by majc2 2 years ago | 86 comments

Blog post evaluating finetuned Mistral, Llama3 and Solar LLMs against OpenAI's GPT-4 on accuracy for structured data extraction from press releases.

6 weeks of Claude Code(blog.puzzmo.com)

543 points by mike1o1 1 year ago | 543 comments

Puzzmo blog post by Orta Therox reflecting on six weeks of using Claude Code and how it changed his approach to writing and maintaining code.