Hacker News: kleyd

New comment by kleyd in "Context Is Software, Weights Are Hardware"

kleyd — Wed, 22 Apr 2026 10:47:17 +0000

Your conclusion touches on this, but I think the brain analogy is stronger than the hardware/software dichotomy.

It is also my very uninformed intuition: https://news.ycombinator.com/item?id=44910353

Also interesting to think about: could a single system be generally intelligent, or is a certain bias actually a power. Can we have billions of models, each with their own "experience"

New comment by kleyd in "Why XML tags are so fundamental to Claude"

kleyd — Sun, 01 Mar 2026 22:25:52 +0000

The main benefit of using XML here seems to be that it forces clearer thinking and formulation from the user.

New comment by kleyd in "Turn Dependabot off"

kleyd — Fri, 20 Feb 2026 23:19:47 +0000

The cooldown is to allow vulnerabilities to be discovered. So auto update on passing tests, which should include an npm audit check.

New comment by kleyd in "Vouch"

kleyd — Sun, 08 Feb 2026 23:01:56 +0000

Thought experiment: strip a forge down to what plain Git can't do: identity (who?), attestations (signed claims about a ref or actor), and policy (do these claims allow this ref update?).

With just those primitives, CI is a service that emits "ci/tested." Review emits "review/approved." A merge controller watches for sufficient attestations and requests a ref update. The forge kernel only evaluates whether claims satisfy policy.

Vouch shifts this even further left: attestations about people, not just code. "This person is trusted" is structurally the same kind of signed claim as "this commit passed CI." It gates participation itself, not just mergeability.

All this should ideally be part of a repo, not inside a closed platform like github. I like it and am curious to see where this stands in 5 years.

New comment by kleyd in "Dev-owned testing: Why it fails in practice and succeeds in theory"

kleyd — Fri, 16 Jan 2026 18:39:32 +0000

Ha, that's certainly a way to build things fool-proof.

New comment by kleyd in "Switch to Jujutsu Already: A Tutorial"

kleyd — Tue, 14 Oct 2025 19:25:02 +0000

I believe this only works when there are no other uncommitted changes.

So you would need to stash after the fixup commit and pop the stash after rebase. Or use autostash.

New comment by kleyd in "Page Object (2013)"

kleyd — Mon, 15 Sep 2025 09:11:10 +0000

It's not a trade-off of clarity just to save developers some extra typing. It's actually improving the clarity by bringing the thing you care about to the foreground: the getting started page having a table of contents with specific items.

New comment by kleyd in "All New Java Language Features Since Java 21"

kleyd — Sat, 06 Sep 2025 18:27:33 +0000

I wouldn't dare say XML is better in this regard, but a good reason to be conservative with the use of annotations is exactly that cmd+clicking them doesn't easily lead to where the behavior is implemented.

New comment by kleyd in "Why LLMs can't really build software"

kleyd — Fri, 15 Aug 2025 09:44:09 +0000

Current LLMs look a lot like a very advanced 'old brain' to me. While context engineering looks like optimizing the working memory.

What's missing is a part with more plasticity that can work in parallel and bi-directionally interact with the current static models in real-time.

This would mean individually trained models based on their experience so that knowledge is not translated to context, but to weight adjustments.

New comment by kleyd in "Getting good results from Claude Code"

kleyd — Sun, 10 Aug 2025 19:56:30 +0000

That matches exactly my experience. Now there are a couple of prototypes to be finished, which still takes time. And higher priority tasks get delayed instead of sped up.

New comment by kleyd in "Getting good results from Claude Code"

kleyd — Fri, 08 Aug 2025 20:53:38 +0000

Does anyone else find themselves starting projects that wouldn't otherwise be worth the time investment, while avoiding Claude Code for the tasks that actually have high priority?

Who has had success using Claude Code on features in older, bigger, messier projects?