Hacker News: uduni

New comment by uduni in "Embarrassingly simple self-distillation improves code generation"

uduni — Sat, 04 Apr 2026 17:20:43 +0000

It's crazy how much better you can make LLM output just by asking "is this the most elegant solution?" In a loop

(Not fine tuning, but interesting none the less. If a model can so easily find a more elegant solution, why didn't it pick that in the first place?)

New comment by uduni in "Sweden goes back to basics, swapping screens for books in the classroom"

uduni — Fri, 03 Apr 2026 05:21:02 +0000

Written language is deep tech itself. There's evidence it changed our brain morphology even. So ya it deeply affected kids abilities, for example memorizing long poems or whatever.

Digital tech is here to stay...

New comment by uduni in "The beginning of programming as we'll know it?"

uduni — Fri, 03 Apr 2026 05:18:04 +0000

It's a skill set just like coding. You can embrace an elevated workflow where you can forget about the specific syntax and focus on the architecture and integration. It takes time to intuit what exactly the models are bad at, so you can forsee hallucinations and prevent them from happening in the first place. Yes you can write 1 line faster than Claude, but what about 10 lines? 100? 1000?

New comment by uduni in "Cursor 3"

uduni — Thu, 02 Apr 2026 21:51:25 +0000

I guess they are assuming LLMs will just get better and better until youn don't look at code at all.

Ignoring the fact that software will just keep getting more and more complex and interconnected... There will always be a new frontier or code and UX

New comment by uduni in "The Claude Code Leak"

uduni — Thu, 02 Apr 2026 06:34:55 +0000

Sure... A good harness can be built in 1 day tho. A good model is 1000x more sophisticated

New comment by uduni in "The Claude Code Leak"

uduni — Thu, 02 Apr 2026 06:30:48 +0000

I've been running a custom harness in production for months (code gen on cloud boxes), it's quite simple (<500 LOC). The model can use sed or other nice bash tricks to efficiently read. U really don't need any tool besides bash plus a good system prompt. Subagents are the same as the main agent (end with a summary). U can just remove tool results (oldest first) to save context, the model can read again if it needs to. High quality memory is the only difficult part. But that can also be solved with high quality documentation

New comment by uduni in "The Anti-Intellectualism of Silicon Valley Elites"

uduni — Thu, 02 Apr 2026 06:01:08 +0000

And? I just joined HN and I like coding with AI. Is it a problem to have a different opinion from you?

New comment by uduni in "The Claude Code Leak"

uduni — Thu, 02 Apr 2026 05:58:58 +0000

" The real value in the AI ecosystem isn’t the model or the harness — it’s the integration of both working seamlessly together. "

Wut? The value in the ecosystem is the model. Harnesses are simple. Great models work nearly identically in every harness

New comment by uduni in "The revenge of the data scientist"

uduni — Wed, 01 Apr 2026 21:22:58 +0000

So true... I get more mileage from just watching an agent work than building sophisticated LLM-as-judge workflows

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

uduni — Wed, 01 Apr 2026 06:39:51 +0000

Slop becomes impossible to maintain, and eventually product velocity slows down. Maybe it's ok for an ultra simple todo app, but for most apps code quality absolutely matters... Users expect snappy UX and all the new bells and whistles.

Why did Whatsapp grow so big while thousands of previous chat apps didn't code quality (scalability)

New comment by uduni in "AI isn't killing jobs, it's 'unbundling' them into lower-paid chunks"

uduni — Sun, 29 Mar 2026 23:22:15 +0000

How is this different from previous layers of abstraction? React/JS dev don't have to think about memory management or a million other things that C++ application devs did. Instead that cognitive load is unbundled onto the framework maintainers, and frontend devs can be much more productive.

Obviously react/js didn't cause job apocalypse... Quite the opposite. It's just another abstraction layer making it possible to build a full application with less text. Prompts are the same pattern again IMO

New comment by uduni in "Coding agents could make free software matter again"

uduni — Sun, 29 Mar 2026 22:41:59 +0000

There's too much value in familiar UX. "Don't make the user think" is the golden rule these days. People used to have mental bandwidth for learning new interfaces... But now people expect uniformity