stevekrouse

stevekrouse on Hacker News

AI gets about 10x cheaper every year

Posted by stevekrouse on Friday October 23, 2026 @05:04PM
from the stevekrouse.com dept.

https://stevekrouse.com/10x

( Read More... | no comments | 2 points | on HN )

Software Finds Its Natural Size

Posted by stevekrouse on Wednesday October 21, 2026 @02:28PM
from the arbesman.substack.com dept.

https://arbesman.substack.com/p/software-finds-its-natural-size

( Read More... | no comments | 2 points | on HN )

What Shall I Teach My Son?

Posted by stevekrouse on Monday October 19, 2026 @03:06PM
from the stevekrouse.com dept.

https://stevekrouse.com/ends

( Read More... | no comments | 2 points | on HN )

Justice for CSS

Posted by stevekrouse on Monday September 28, 2026 @02:41PM
from the wired.com dept.

https://www.wired.com/story/justice-for-css/

( Read More... | no comments | on HN )

After Work, We'll Have Each Other

Posted by stevekrouse on Wednesday September 02, 2026 @05:30PM
from the asteriskmag.com dept.

https://asteriskmag.com/issues/15/after-work-we-ll-have-each-other

( Read More... | no comments | on HN )

Connecting every app to every other app

Posted by stevekrouse on Wednesday September 02, 2026 @01:41PM
from the blog.val.town dept.

https://blog.val.town/connectors

( Read More... | no comments | on HN )

A docs page is a long and complex search query to find AI agents

Posted by stevekrouse on Tuesday September 01, 2026 @05:04PM
from the blog.val.town dept.

https://blog.val.town/aeo

( Read More... | 1 comment | 3 points | on HN )

Abottom

Posted by stevekrouse on Friday August 21, 2026 @11:59AM
from the abottom.org dept.

https://abottom.org/

( Read More... | no comments | 2 points | on HN )

Our Self-Building Slackbot

Posted by stevekrouse on Thursday August 13, 2026 @10:56AM
from the blog.val.town dept.

https://blog.val.town/slackbot-townie

( Read More... | no comments | on HN )

Ethical Cold Outreach

Posted by stevekrouse on Tuesday August 11, 2026 @02:06PM
from the blog.val.town dept.

https://blog.val.town/ethical-cold-outreach

( Read More... | 78 comments | 2 points | on HN )

Report from the Security Mines

Posted by stevekrouse on Tuesday August 11, 2026 @02:06PM
from the blog.val.town dept.

https://blog.val.town/security

( Read More... | no comments | 2 points | on HN )

Docfooding: Eating Our Own Documentation

Posted by stevekrouse on Tuesday August 11, 2026 @02:06PM
from the blog.val.town dept.

https://blog.val.town/docfooding

( Read More... | no comments | 3 points | on HN )

I RL-finetuned an LLM to unslop my writing

Posted by stevekrouse on Tuesday August 04, 2026 @06:10AM
from the castform.com dept.

https://castform.com/blog/unslop/

( Read More... | no comments | 3 points | on HN )

The agent principal-agent problem

Posted by stevekrouse on Tuesday July 21, 2026 @03:58PM
from the crawshaw.io dept.

https://crawshaw.io/blog/agent-principal-agent

( Read More... | no comments | on HN )

Re:Ask HN: What are your favorite blogs not about AI? on Monday July 20, 2026 @08:13AM (#48977707)

https://worrydream.com

https://macwright.com/

https://www.petemillspaugh.com/

https://www.geoffreylitt.com/

https://maggieappleton.com/

https://www.robinsloan.com/

https://thesephist.com/

https://wattenberger.com/

http://conal.net/

https://www.todepond.com/

https://devonzuegel.com/

https://nadia.xyz/

https://adamwiggins.com/

http://glench.com/

https://ncase.me/

Classic from my old Haskell professor: https://byorgey.wordpress.com/2009/01/12/abstraction-intuiti...

Re:Learning to code is still worthwhile on Monday July 06, 2026 @06:14PM (#48811193)

Ah damn, sorry about that. I removed my footer "ads" in response to this feedback. Appreciate it.

Learning to code is still worthwhile

Posted by stevekrouse on Monday July 06, 2026 @04:59PM
from the stevekrouse.com dept.

https://stevekrouse.com/learn-to-code

( Read More... | 313 comments | 90 points | on HN )

Chad Fowler's "Phoenix Architecture"

Posted by stevekrouse on Tuesday June 30, 2026 @03:56PM
from the stevekrouse.com dept.

https://stevekrouse.com/phoenix

( Read More... | no comments | 2 points | on HN )

Scoped Blob Storage

Posted by stevekrouse on Thursday June 11, 2026 @11:55AM
from the blog.val.town dept.

https://blog.val.town/scoped-blob-storage

( Read More... | 2 comments | on HN )

Re:From Supabase to Clerk to Better Auth on Wednesday May 06, 2026 @10:40PM (#48044781)

back online!

From Supabase to Clerk to Better Auth

Posted by stevekrouse on Wednesday May 06, 2026 @01:19PM
from the blog.val.town dept.

https://blog.val.town/better-auth

( Read More... | 240 comments | 115 points | on HN )

AI agents are briefly overhyped

Posted by stevekrouse on Saturday May 02, 2026 @06:32PM
from the stevekrouse.com dept.

https://stevekrouse.com/agent-hype

( Read More... | no comments | on HN )

Re:Reports of code's death are greatly exaggerated on Monday March 23, 2026 @12:23PM (#47491626)

I don't disagree with anything you just said

Roots – Return Old Online Things to Your Own Site

Posted by stevekrouse on Monday March 23, 2026 @06:39AM
from the macwright.com dept.

https://macwright.com/2026/03/12/roots

( Read More... | no comments | 2 points | on HN )

Re:Reports of code's death are greatly exaggerated on Sunday March 22, 2026 @08:22PM (#47483900)

Isaac!!!!! I had no idea that was you! Too funny! Emily and I are dying

Yes, we'd love to visit!

Re:Reports of code's death are greatly exaggerated on Sunday March 22, 2026 @06:41PM (#47483033)

I think we're in agreement. My Dijkstra quote is the perfect rejoinder to your Wittgenstein:

The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise.

— Edsger Dijkstra

Re:Reports of code's death are greatly exaggerated on Sunday March 22, 2026 @04:00PM (#47481507)

Such a perfect quote! Thank you! Will add it to my collection

Re:Reports of code's death are greatly exaggerated on Sunday March 22, 2026 @04:00PM (#47481492)

Genuine!

Re:Reports of code's death are greatly exaggerated on Sunday March 22, 2026 @03:58PM (#47481473)

That's not my argument at all! Though I can see why you took that away; my bad for not making my argument clearer.

I believe that even when we have AGI, code will still be super valuable because it'll be how we get precise abstractions into human heads, which is necessary for humans to be able to bring informed opinions to bear.

Re:Steve-eval – getting AI to write like me on Sunday March 22, 2026 @03:45PM (#47481322)

Fair! I appreciate the reply.