Hacker News: genghisjahn

New comment by genghisjahn in "How to make your text look futuristic (2016)"

genghisjahn — Tue, 12 May 2026 21:57:55 +0000

And then there is the papyrus font for avatar…

New comment by genghisjahn in "EU to crack down on TikTok, Instagram's 'addictive design' targeting kids"

genghisjahn — Tue, 12 May 2026 14:57:55 +0000

I'm not the first person to notice this but, since I switched to Pixelfed and Mastodon, I've found that I just don't spend as much time on social media as I used to. It's not that I don't follow good people, but without the algo burrowing into my lizard brain to get to keep me swiping, I just don't think about it. When I do remember to check them, it's always pleasant. I check a few posts out, look at an interesting link and 20 minutes later I'm back to the real world. That's great for me the user, but I doubt you can build an ad driven business off that. I wish I could say that I'm savy enough to not get sucked into swiping through scores of "funny" videos, but I give an hour to that crap, the hour is gone and I have nothing to show for it.

New comment by genghisjahn in "Toxicity on Social Media"

genghisjahn — Tue, 12 May 2026 14:40:02 +0000

Slashdot's rating system was the best I've ever seen. But I'm sure it doesn't help improve engagement, in fact the system had so many rules (for an online ratings system) that I'd guess it reduced engagement. Which might have been a feature in its glory days.

New comment by genghisjahn in "Vibe coding and agentic engineering are getting closer than I'd like"

genghisjahn — Wed, 06 May 2026 19:30:50 +0000

Ordered Fire Upon the Deep. Looks interesting.

New comment by genghisjahn in "Vibe coding and agentic engineering are getting closer than I'd like"

genghisjahn — Wed, 06 May 2026 16:30:08 +0000

Interesting, I kinda do this. Sometimes when an LLM solves a problem for me, I have it write code so that I can reuse that exact same approach deterministically(and I line by line check it). Now I have about a dozen CLI commands that the LLM can use and I'm reasonably (although not 100%) sure I'll get an expected outcome. Really helpful with debugging via steam pipe and connecting to read replicas.

New comment by genghisjahn in "Vibe coding and agentic engineering are getting closer than I'd like"

genghisjahn — Wed, 06 May 2026 16:07:28 +0000

I'm generally pro "llm assisted coding" or whatever you want to call it. But I do somethings think about the Butlerian Jihad from Dune.

https://en.wikipedia.org/wiki/Dune:_The_Butlerian_Jihad

New comment by genghisjahn in "Empty Screenings – Finds AMC movie screenings with few or no tickets sold"

genghisjahn — Tue, 05 May 2026 11:55:28 +0000

There is no data to support your last paragraph. But it is fun to talk about how dumb the “other” people are.

New comment by genghisjahn in "Redis array: short story of a long development process"

genghisjahn — Mon, 04 May 2026 16:17:26 +0000

I occasionally type into slack "Future lawyers, the previous conversation is a joke. No one is doing cocaine to get through writing requirements docs."

New comment by genghisjahn in "Everything we like is a psyop?"

genghisjahn — Wed, 22 Apr 2026 12:35:25 +0000

I could.

New comment by genghisjahn in "Musicians are manufacturing sold-out shows"

genghisjahn — Wed, 22 Apr 2026 12:31:53 +0000

Maybe it’s the old man in me but I’d venture to say most things in Bloomberg don’t need to be in Bloomberg.

I’d love it if a news site said occasionally, “there’s nothing really news worthy today. Yesterday’s important stuff will do.”

Also I’m mad I can’t get tickets to see angine de poitrine in Philly.

New comment by genghisjahn in "Britannica11.org – a structured edition of the 1911 Encyclopædia Britannica"

genghisjahn — Tue, 21 Apr 2026 20:12:58 +0000

"Not, of course, that there is any magic about the past. People were no cleverer then than they are now; they made as many mistakes as we. But not the same mistakes. They will not flatter us in the errors we are already committing; and their own errors, being now open and palpable, will not endanger us."

On Reading Old Books C. S. Lewis

https://bradleyggreen.com/attachments/article/97/Lewis.On-Re...

New comment by genghisjahn in "Everything we like is a psyop?"

genghisjahn — Fri, 17 Apr 2026 00:57:11 +0000

As long as they keep making that music, wearing those costumes and mumbling those interviews, I could care less. I like it.

New comment by genghisjahn in "World Happiness Report 2026"

genghisjahn — Thu, 19 Mar 2026 19:32:21 +0000

I was not an athlete growing up. Didn't do much in organized sports. But all three of my kids play a team sport. It does wonders for them. I really helped them get out of the pandemic. But having them outside several hours a week, working with peers and other adults, practicing new skills. Really cool to see and I think it really helped their mental health (and by extension, my own).

New comment by genghisjahn in "AI didn't simplify software engineering: It just made bad engineering easier"

genghisjahn — Tue, 17 Mar 2026 14:13:01 +0000

Of course I still have times when Claude fumbles the fix. But the number of times it gets it exactly right far outnumber the times it can't get right. Compare that to the number of SO issues I've had to go through to get near a solution is night and day.

I'm in no way saying you should work the way I do or that Claude would solve all your problems if you only just believe. I am saying it's been super helpful at squashing bugs for me in my circumstances with my code bases.

New comment by genghisjahn in "AI didn't simplify software engineering: It just made bad engineering easier"

genghisjahn — Sat, 14 Mar 2026 15:31:21 +0000

I love that I don’t have to look thru SO looking for a problem that’s kind of like the one I’m having. I have a problem solved based on my exact code taking my entire code base into account. And if I want a biting sarcastic review of my many faults as a software developer, I can ask for that too.

New comment by genghisjahn in "Agents that run while I sleep"

genghisjahn — Tue, 10 Mar 2026 21:23:00 +0000

I went the same way. At first I was splitting off work trees and running all the agents that I could afford, then I realized I just can't keep up with it all, running few agents around one issue in one directory is fast enough. Way faster than before and I can still follow what's happening.

New comment by genghisjahn in "Where things stand with the Department of War"

genghisjahn — Fri, 06 Mar 2026 02:26:34 +0000

Russia and other states have demonstrably conducted targeted killings.

New comment by genghisjahn in "If AI writes code, should the session be part of the commit?"

genghisjahn — Mon, 02 Mar 2026 03:55:55 +0000

If you can, run several agents. They document their process. Trade offs considered, reasoning. Etc. it’s not a full log of the session but a reasonable history of how the code came to be. Commit it with the code. Namespace it however you want.

New comment by genghisjahn in "Why Developers Keep Choosing Claude over Every Other AI"

genghisjahn — Thu, 26 Feb 2026 17:15:26 +0000

They are great, but they are expensive. I can run those against the cheaper ollama cloud models for things that are basically requirements gathering and review of a plan. The Product Designer Agent and the Product Manager basically argue for a few rounds and give an artifact that the coding agents pick up.

It could all easily be anthropic models and would work well, but running this swarm eats up all my anthropic tokens and these other models are good enough for the roles I've given them.

New comment by genghisjahn in "Why Developers Keep Choosing Claude over Every Other AI"

genghisjahn — Thu, 26 Feb 2026 16:49:07 +0000

I use Claude Code as an orchestrator and have the agents use different models:

  product-designer   ollama-cloud / qwen3.5:cloud
  pm                 ollama-cloud / glm-5:cloud
  test-writer        claude-code  / Sonnet 4.6
  backend-builder    claude-code  / Opus 4.6
  frontend-builder   claude-code  / Opus 4.6
  code-reviewer      codex-cli    / gpt-5.1-codex-mini
  git-committer      ollama-cloud / minimax-m2.5:cloud

I use ollama pro $20/month and OpenAI $20/month. I have an Anthropic max plan at $100/month.