Hacker News: zingar

New comment by zingar in "Prolog Coding Horror"

zingar — Mon, 18 May 2026 08:09:07 +0000

That sounds intuitively right but breaks down when you ask “inefficient at what?”. Are you efficient with CPU cycles or efficient with human working memory?

New comment by zingar in "Zerostack – A Unix-inspired coding agent written in pure Rust"

zingar — Mon, 18 May 2026 07:59:27 +0000

Edit: I lost the context that this is about building devtools where you can’t just throw more hardware at the problem. But perhaps my answer still explains the reality: anthropic builds Claude with Claude so Claude needs to be easy to build with Claude.

Easier to read for humans is easy to read for LLMs. A more expressive language will bring about fewer misunderstandings when you apply stochastic tools like LLMs.

Just be sure you don’t choose something heavier/slower that is not more expressive.

New comment by zingar in "A recent experience with ChatGPT 5.5 Pro"

zingar — Sat, 09 May 2026 09:29:35 +0000

The post talks about LLM+human contributions being recognized in some different category from human-only. But is it possible to spot the difference between the two?

New comment by zingar in "Agents need control flow, not more prompts"

zingar — Fri, 08 May 2026 12:56:16 +0000

This is a refreshing take but I’d really have liked an example for contrast.

New comment by zingar in "Simulacrum of Knowledge Work"

zingar — Thu, 30 Apr 2026 16:21:10 +0000

I find misapplication of anti-smell techniques a pretty cheap indicator that I’m looking at LLM garbage. I think they’re not really usefully engaging with that stuff yet.

New comment by zingar in "I have officially retired from Emacs"

zingar — Wed, 29 Apr 2026 22:53:15 +0000

How do you have the “modify LLM state from within” working? I can have it modify my config but I don’t know how to get it to eval and improve arbitrary elisp.

New comment by zingar in "I have officially retired from Emacs"

zingar — Wed, 29 Apr 2026 22:49:30 +0000

Absolutely baffled too. I was expecting that they preferred the vim philosophy of small tools that do one thing well, but no. So you like modal editing, well you’ve got it right there in emacs. Why that of all the potential gripes you might have with emacs?

New comment by zingar in "I have officially retired from Emacs"

zingar — Wed, 29 Apr 2026 22:43:42 +0000

I’d like a concrete example on how you’re actually controlling emacs with LLMs. Is ECA the part that does that?

New comment by zingar in "Simulacrum of Knowledge Work"

zingar — Sat, 25 Apr 2026 21:24:36 +0000

I think there’s a weaker claim that holds true: we were able to ignore lots of content based on the superficial (and pay proper attention to work that passed this test) and now we are overwhelmed because everything meets the superficial criteria and we can’t pay proper attention to all of it.

Why software fundamentals matter more than ever [video]

zingar — Fri, 24 Apr 2026 09:58:09 +0000

Article URL: https://www.youtube.com/watch?v=v4F1gFy-hqg

Comments URL: https://news.ycombinator.com/item?id=47887986

Points: 2

# Comments: 0

New comment by zingar in "Ping-pong robot beats top-level human players"

zingar — Wed, 22 Apr 2026 22:03:00 +0000

Chess players learned to exploit chess computers’ weaknesses in the beginning too, but they can’t any longer. This version of the robot might not learn continuously, but the next will be better.

New comment by zingar in "Technical, cognitive, and intent debt"

zingar — Wed, 22 Apr 2026 20:07:11 +0000

We have confidence in the extra code a compiler generates because it’s deterministic. We don’t have that in LLMs, neither those that wrote nor read the code.

New comment by zingar in "Less human AI agents, please"

zingar — Wed, 22 Apr 2026 08:56:16 +0000

What's your hypothesis about the relationship between TODOs and action?

New comment by zingar in "Less human AI agents, please"

zingar — Wed, 22 Apr 2026 08:55:14 +0000

How the neural networks produce such surprisingly human characteristics is an open question with a ton of research going into it. Explaining this is a bit more than what one smart person can achieve.

New comment by zingar in "Less human AI agents, please"

zingar — Tue, 21 Apr 2026 08:36:56 +0000

I have the same experience of reversing intentional steps I've made, but with Claude Code. I find that committing a change that I want to version control seems to stop that behaviour.

Long context as disadvantage is pretty well discussed, and agent-native compaction has been inferior to having it intentionally build the documentation that I want it to use. So far this has been my LLM-coding superpower. There are also a few products whose entire purpose is to provide structure that overcomes compaction shortcomings.

When Geoff Huntley said that Claude Code's "Ralph loop" didn't meet his standards ("this aint it") the major bone of contention as far as I can see was that it ran subagents in a loop inside Claude Code with native compaction; as opposed to completely empty context.

I do see hints that improving compaction is a major area of work for agent-makers. I'm not certain where my advantage goes at that point.

New comment by zingar in "Less human AI agents, please"

zingar — Tue, 21 Apr 2026 08:30:05 +0000

Interesting that what you're talking about as ASI is "as capable of handling explicit requirements as a human, but faster". Which _is_ better than a human, so fair play, but it's striking that this requirement is less about creativity than we would have thought.

New comment by zingar in "Less human AI agents, please"

zingar — Tue, 21 Apr 2026 08:27:40 +0000

The work where I've done well in my life (smashing deadlines, rescuing projects) has so often come because I've been willing to push back on - even explicitly stated - requirements. When clients have tried to replace me with a cheaper alternative (and failed) the main difference I notice is that the cheaper person is used to being told exactly what to do.

Maybe this is more anthropomorphising but I think this pushing back is exactly the result that the LLMs are giving; but we're expecting a bit too much of them in terms of follow-up like: "ok I double checked and I really am being paid to do things the hard way".

New comment by zingar in "Less human AI agents, please"

zingar — Tue, 21 Apr 2026 08:22:43 +0000

Fascinating. This is invisible to me, what anthropomorphising did you notice that stood out?

New comment by zingar in "Less human AI agents, please"

zingar — Tue, 21 Apr 2026 08:20:03 +0000

The article makes it seem like the author expected this without emptying context in between, which does not yet exist (actually I'm behind on playing with Opus 4.7, the Anthropic claim seems to be that longer sessions are ok now - would be interested to hear results from anyone who has).

New comment by zingar in "Less human AI agents, please"

zingar — Tue, 21 Apr 2026 08:18:46 +0000

> Maybe we should just commit the signature change with a TODO

I'm fascinated that so many folks report this, I've literally never seen it in daily CC use. I can only guess that my habitually starting a new session and getting it to plan-document before action ("make a file listing all call sites"; "look at refactoring.md and implement") makes it clear when it's time for exploration vs when it's time for action (i.e. when exploring and not acting would be failing).