Implementers, Solvers, and Finders(rkoutnik.com)

148 points by kiyanwang 3 years ago | 12 comments

Can GPT pass my programming courses?(lemire.me)

27 points by greghn 3 years ago | 40 comments

Subnormal floating-point numbers are expensive on Intel processors(lemire.me)

53 points by zdw 1 month ago | 41 comments

Self Documenting Code Is Bullshit(v01.io)

6 points by klausbreyer 2 years ago | 0 comments

Mirror_bridge – C++ reflection for generating Python/JS/Lua bindings(chico.dev)

26 points by fthiesen 10 months ago | 9 comments

Hotspot performance engineering fails(lemire.me)

160 points by slimsag 3 years ago | 85 comments

The force-feeding of AI features on an unwilling public(honest-broker.com)

330 points by imartin2k 1 year ago | 279 comments

Ted Gioia essay on The Honest Broker arguing tech companies are forcing unwanted AI features on users, calling it tyranny rather than innovation.

Nobody knows how to build with AI yet(worksonmymachine.substack.com)

475 points by Stwerner 1 year ago | 368 comments

Scott Werner's Substack essay arguing nobody yet knows how to build software with AI, drawing on building Protocollie in four days without touching the code.

Thought as a Technology (2016)(cognitivemedium.com)

4 points by tobr 26 days ago | 0 comments

Michael Nielsen's 2016 essay on how computer interfaces can serve as cognitive technologies that expand the range of human thought.

Working quickly is more important than it seems (2015)(jsomers.net)

444 points by cal85 3 years ago | 164 comments

James Somers' 2015 blog essay arguing that working quickly matters more than it seems; the page loaded as a 500 server error.

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.

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.