Top all-time · #11723
Josh Moody
Personal blog · joshmoody.org/blogaiprogramming
Josh Moody's personal blog at joshmoody.org covers ai and programming. Since 2025, 6 different Hacker News readers have linked it 10 times, most often “How to Passive-Aggressively Shame People Who Use LLMs Selfishly”. It is still writing: the last post was on 2026-09-16, and you can follow it by feed.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
Comments only link these posts without judging them. The linked posts cover shaming people who paste LLM output, and a queuing-theory calculator for how agents or PR reviews slow down throughput.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Josh Moody's homepage
Most-linked posts?
- How to Passive-Aggressively Shame People Who Use LLMs Selfishly2 people · 3 mentions · first linked 2026-06-24
- Programming with Less Than Nothing2 people · 2 mentions · first linked 2025-10-23
- How Many Coding Agents Should You Run in Parallel?2 people · 2 mentions · first linked 2026-03-02
What Hacker News says?
Related: Don't Be a Meat Proxy: https://gruhn.me/blog/2026-08-03/ No Meat Proxy: https://nomeatproxy.com/ How to Passive-Aggressively Shame People Who Use LLMs Selfishly: https://joshmoody.org/blog/selfish-ai/ AI;DR: https://www.rickmanelius.com/p/aidr-ai-didnt-read
Comment linking /blog/selfish-ai/
on “Don't Paste the AI, please”Submitted Programming with Less Than Nothing as a story · 468 points
HN discussionRelated: Don't Be a Meat Proxy: https://gruhn.me/blog/2026-08-03/ No Meat Proxy: https://nomeatproxy.com/ How to Passive-Aggressively Shame People Who Use LLMs Selfishly: https://joshmoody.org/blog/selfish-ai/
Comment linking /blog/selfish-ai/
on “AI;DR (AI; Didn't Read)”Submitted Prediction: The Shopify CEO's Pull Request Will Never Be Merged nor Closed as a story · 6 points
HN discussionLambda calculus is a model of computation. A pretty lightweight model that can still do everything that other programming languages can. Combinators are an even simpler model of computation that is still equally powerful. That simplicity / power ratio is what makes them cool. A while back I built all the way up to FizzBuzz from just S and K combinators. Took days of doing all the math by hand, lol. Here's my write u…
Comment linking /blog/programming-with-less-than-nothing/
on “Combinators”Submitted How to Passive-Aggressively Shame People Who Use LLMs Selfishly as a story · 3 points
HN discussionI made a queuing theory calculator for this: https://joshmoody.org/blog/number-of-agents/#number-of-agent... Although you'll have to mentally replace the word "agent" with "PR" for it to make sense in this context. The math is the same. It all boils down to how much those context switches costs you. If it's a large cost, then you can get a huge productivity boost by increasing review speed. In the "show calculations…
Comment linking /blog/number-of-agents/
on “Every layer of review makes you 10x slower”Submitted How Many Coding Agents Should You Run in Parallel? as a story · 1 points
HN discussionSubmitted How Many Coding Agents Should You Run in Parallel? as a story · 1 points
HN discussionSubmitted Advent of Code vs. Weird Programming Languages as a story · 1 points
HN discussion