Lets Have Three Abstraction Layers(minimal.app)

70 points by arthurofbabylon 3 years ago | 22 comments

LLMs Are Not a Higher Level of Abstraction(lelanthran.com)

96 points by lelanthran 5 months ago | 89 comments

LLMs bring new nature of abstraction – up and sideways(martinfowler.com)

49 points by tudorizer 1 year ago | 39 comments

What will LLM-powered software look like in the medium-term future?(vishnumenon.com)

176 points by vishnumenon 3 years ago | 187 comments

A Conceptual Model for Storage Unification(jack-vanlightly.com)

19 points by avinassh 1 year ago | 2 comments

The future of everything is lies, I guess: Where do we go from here?(aphyr.com)

675 points by aphyr 6 months ago | 695 comments

Final installment of Aphyr's essay series on LLMs and society, discussing where to go from here given the harms and implications of machine learning.

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.

The new skill in AI is not prompting, it's context engineering(philschmid.de)

832 points by robotswantdata 1 year ago | 467 comments

Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.

Cognitive load is what matters(github.com)

1392 points by nromiun 1 year ago | 488 comments

GitHub repository by zakirullin containing an essay arguing that reducing cognitive load is what matters most in software development, with translations.

I'm addicted to being useful(seangoedecke.com)

519 points by swah 9 months ago | 265 comments

Sean Goedecke's blog essay on loving his software engineering job because he is driven by being useful, drawing on Gogol's The Overcoat.

There's no reason for software to be slow anymore(danluu.com)

592 points by Jach 2 months ago | 442 comments

Dan Luu essay arguing that LLM coding agents make specialized performance optimization cheap, illustrated with optimizing a regex engine for specific workloads.

Imaginary problems are the root of bad software(cerebralab.com)

834 points by deofoo 3 years ago | 358 comments

Blog essay on Cerebralab arguing that bad software stems from developers solving imaginary problems rather than real user needs.