I'm done making desktop applications (2009)(kalzumeus.com)

165 points by claxo 6 months ago | 182 comments

Ideal OS: Rebooting the Desktop Operating System (2017)(joshondesign.com)

63 points by mmphosis 2 years ago | 44 comments

UI is hell: four-function calculators(lcamtuf.substack.com)

198 points by surprisetalk 1 year ago | 115 comments

Waymo the Leapfrog(loeber.substack.com)

65 points by loeber 2 years ago | 74 comments

Why I'm Done Making Desktop Applications (2009)(kalzumeus.com)

35 points by mooreds 2 years ago | 31 comments

Revisiting the NetBSD Build System(blogsystem5.substack.com)

120 points by abhi9u 1 year ago | 13 comments

Practical UX for startups surviving without a designer(tibinotes.com)

387 points by tb8424 1 year ago | 156 comments

A Substack essay by Tibi Iorga on how startups can work out their user experience without a dedicated designer, time, or budget.

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.

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.

LLMs work best when the user defines their acceptance criteria first(blog.katanaquant.com)

411 points by dnw 7 months ago | 368 comments

Substack essay from Vagabond Research arguing that LLMs produce plausible rather than correct code, using a simple database primary key lookup test as an example.

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.

TODOs aren't for doing(sophiebits.com)

380 points by todsacerdoti 1 year ago | 218 comments

A blog post by Sophie Alpert arguing that TODO comments are valuable as documentation of known issues even if never acted on, and shouldn't be auto-deleted or tracked.