LLMs as Compilers(resync-games.com)

28 points by kadhirvelm 1 year ago | 38 comments

C for Rust programmers(bd103.dev)

154 points by xyproto 18 days ago | 161 comments

A blog post by a programmer who learned Rust first, listing surprising details and quirks of C for Rust programmers learning the language.

Raku: A language for gremlins(buttondown.email)

355 points by azhenley 3 years ago | 180 comments

Hillel Wayne's Computer Things newsletter post describing the Raku programming language as a quirky language 'by gremlins, for gremlins'.

Why is Common Lisp not the most popular programming language?(daninus14.github.io)

65 points by kryptiskt 2 years ago | 143 comments

Emacs Lisp shorthands as namespacing system(andreyorst.gitlab.io)

78 points by gjvc 3 years ago | 15 comments

Why LLMs can't really build software(zed.dev)

321 points by srid 1 year ago | 196 comments

A Zed blog post by Conrad Irwin arguing that LLMs cannot really build software, drawing on his experience of what effective software engineers do.

Why I Chose Common Lisp(blog.djhaskin.com)

328 points by djha-skin 1 year ago | 145 comments

Blog post explaining why the author left Clojure after seven years over slow startup times and chose Common Lisp as their hobby language.

The future of software development is software developers(codemanship.wordpress.com)

376 points by cdrnsf 10 months ago | 471 comments

A Codemanship blog post arguing that the future of software development still depends on human software developers.

I built a programming language that LLMs can't use(blog.picheta.me)

244 points by dom96 8 days ago | 179 comments

Blog post by Dominik Picheta introducing KillSwitch, a programming language he designed so that large language models cannot use it.

The path to ubiquitous AI (17k tokens/sec)(taalas.com)

804 points by sidnarsipur 8 months ago | 436 comments

Taalas blog post by Ljubisa Bajic arguing that latency and cost limit AI adoption and presenting its approach to very fast (17k tokens/sec) inference hardware.

Prevent cognitive debt by manually retyping LLM-generated code(ankursethi.com)

502 points by mpweiher 2 months ago | 413 comments

A personal blog post arguing that developers should manually retype code generated by LLM coding assistants to keep understanding it and avoid cognitive debt.

Local AI needs to be the norm(unix.foo)

1767 points by cylo 5 months ago | 699 comments

Blog post on unix.foo arguing that apps should run AI models locally rather than relying on API calls to OpenAI or Anthropic.