Hacker News: shinycode

New comment by shinycode in "Measuring Claude 4.7's tokenizer costs"

shinycode — Sat, 18 Apr 2026 11:50:14 +0000

Very nice insight, that’s where the value is, even with a lot of time refactoring, testing and reviewing the compressed code phase is so much gziped than it’s still worth it to use an imperfect LLM. Even with humans we have all those post phases so great structure around the code generation leads to a lot of gains. It depends on industries and what’s being developed for sure

New comment by shinycode in "Muse Spark: Scaling towards personal superintelligence"

shinycode — Thu, 09 Apr 2026 06:54:52 +0000

But at some point even if the product is useful if it costs twice what is getting in, won’t that be a problem ?

New comment by shinycode in "Gemma 4 on iPhone"

shinycode — Mon, 06 Apr 2026 14:24:58 +0000

Probably asked what’s the Answer to the Ultimate Question of Life, the Universe, and Everything

New comment by shinycode in "Slop is not necessarily the future"

shinycode — Tue, 31 Mar 2026 21:20:18 +0000

That’s non sense. Every software people pay or use as their professional tool should be carefully crafted. Would you buy a house/car/anything or value knowing that people who built it don’t care about their craft as long as you got it in your hands and pay for it ? Or maybe you produce something cheap and worthless

New comment by shinycode in "When do we become adults, really?"

shinycode — Sun, 29 Mar 2026 11:44:53 +0000

Agreed, but it proves the point that having kids does not makes you an adult

New comment by shinycode in "When do we become adults, really?"

shinycode — Sun, 29 Mar 2026 10:34:41 +0000

So you’ve never seen parents quit and neglect their kids ? That does not exists ?

New comment by shinycode in "When Do We Become Adults, Really?"

shinycode — Sun, 29 Mar 2026 08:55:18 +0000

So all the employees of companies that work in this industry are not adults if they play ? You are targeting a specific fringe of people too broadly.

New comment by shinycode in "When do we become adults, really?"

shinycode — Sun, 29 Mar 2026 08:53:35 +0000

I know many people who have children and are not adults. And someone who never have kids will never be adult ?

New comment by shinycode in "Desk for people who work at home with a cat"

shinycode — Sat, 28 Mar 2026 08:48:25 +0000

The article is useless, but the comments about people talking about their cats are priceless. Thank you OP to have ignited this thread, makes me so happy to read about other people love/observations of their cat. Definitely my all time favorite on HN

New comment by shinycode in "Desk for people who work at home with a cat"

shinycode — Sat, 28 Mar 2026 08:45:57 +0000

+1 after many failed attempts to buy useless cat toys, I’ve been really surprised that those are what we loves the most. He can play alone with it for hours and is absolutely crazy happy to play fetch with me. Maybe when I throw the elastic hair is kind of a bird like feature him.

New comment by shinycode in "Coding after coders: The end of computer programming as we know it?"

shinycode — Sat, 14 Mar 2026 12:39:05 +0000

It’s true there’s some magic effect from Claude code’s work. But still, often it’s not exactly the same infra and scaling than production grade. But for a customer I guess that’s perfect, they have a mean to make their own tools instead of relying on platforms to build those tools.

New comment by shinycode in "Coding after coders: The end of computer programming as we know it?"

shinycode — Sat, 14 Mar 2026 12:32:38 +0000

That’s the exact definition our CEO gave of our job this week. That’s how he sees and expects us to work now. I feel some anxiety because that’s too much too fast. We went from « we need to fix every single bug we encounter » to « it doesn’t matter if there’s bugs as long as we ship a feature fast »

New comment by shinycode in "Labor market impacts of AI: A new measure and early evidence"

shinycode — Fri, 06 Mar 2026 09:51:18 +0000

The exact same prompt ? Everything depends on the prompt and it’s different tools. These days the quality and what’s build around the prompt matters as much as the code. We can’t feed generic query.

New comment by shinycode in "The L in "LLM" Stands for Lying"

shinycode — Thu, 05 Mar 2026 16:00:29 +0000

There isn’t just concrete in a house. There is hundreds of things that could vary from house to house (even country to country and laws) so it’s more like the building blocs are not only imports of lib but the language itself (raw materials) which makes it a fit analogy for me

New comment by shinycode in "The L in "LLM" Stands for Lying"

shinycode — Thu, 05 Mar 2026 10:13:27 +0000

No I don’t agree. Just because it’s « boilerplate », that does not mean it’s worthless or doesn’t carry novelty. There is « boilerplate » in building many things, house, cars etc where to add real new stuff it’s « always the same base » but you have to nail that base and there is real value in it. With craft and deep knowledge and pride. Every project is different and not everything can be made from a generic out-of-shelf product

New comment by shinycode in "Something is afoot in the land of Qwen"

shinycode — Thu, 05 Mar 2026 07:33:00 +0000

If found it better to split in smaller tasks from a first overall analysis and make it do only that subtask and make it give me the next prompt once finished (or feed that to a system of agents). There is a real threshold from where quality would be lost.

New comment by shinycode in "When AI writes the software, who verifies it?"

shinycode — Tue, 03 Mar 2026 22:39:26 +0000

Our CEO, an expert in marketing has discovered Claude Code and is the one having the most open PR of all developers and is pushing for us to « quickly review ». He does not understand why review are so slow because it’s « the easiest part ». We live in a new world.

New comment by shinycode in "Meta’s AI smart glasses and data privacy concerns"

shinycode — Tue, 03 Mar 2026 12:11:05 +0000

Discreet is not the same thing as embedded in your face with no hands involved and indiscernible from regular glasses.

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

shinycode — Mon, 02 Mar 2026 08:00:49 +0000

Thanks for the link ! I’m very curious about their choices and methods, I’ll try it

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

shinycode — Mon, 02 Mar 2026 07:58:04 +0000

I also do that and it works quite well to iterate on spec md files first. When every step is detailed and clear and all md files linked to a master plan that Claude code reads and updates at every step it helps a lot to keep it on guard rails. Claude code only works well on small increments because context switching makes it mix and invent stuff. So working by increments makes it really easy to commit a clean session and I ask it to give me the next prompt from the specs before I clear context. It always go sideways at some point but having a nice structure helps even myself to do clean reviews and avoid 2h sessions that I have to throw away. Really easier to adjust only what’s wrong at each step. It works surprisingly well