Hacker News: zingar

New comment by zingar in "Why Software Factories Fail (or: harness engineering is not enough)"

zingar — Thu, 23 Jul 2026 19:36:45 +0000

Enjoyed most of this but unconvinced by the program design part. If I see an agent writing function signatures or listing which functions to edit in a plan that tells me that I’ve given it too big a vertical slice. I always delete the code guesses. The thing that writes the code must always spend some time discovering where/what to write or it won’t have the right context. Or put another way: “decide first, act later” always feels worse than act-learn-act.

New comment by zingar in "Judge approves $1.5B Anthropic settlement for pirated books used to train Claude"

zingar — Wed, 22 Jul 2026 08:58:52 +0000

It would be interesting to know what the guardrails are. That would help me with understanding how I can use AI content. For instance I asked Claude to help me draw a diagram to represent a software engineering concept for a public presentation and then I had to stop and think: am I about to just reuse something from a Martin Fowler or Kent Beck book without attribution?

New comment by zingar in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"

zingar — Wed, 15 Jul 2026 11:58:26 +0000

I feel like I'm seeing a maths+AI change from "let's test the limits of LLMs by seeing if they can do useful math" to "LLMs can do useful math, now let's solve lots of problems!", or put a different way the goal has shifted from "interesting exercise for AI" to "making a big difference in math". Am I correct?

Are there practical applications of any these problems being solved? No judgement implied, I'm well aware that "no" only means "not yet".

New comment by zingar in "An agent in 100 lines of Lisp"

zingar — Mon, 13 Jul 2026 07:34:59 +0000

Ah of course, I do have a blind spot with local models.

New comment by zingar in "An agent in 100 lines of Lisp"

zingar — Sun, 12 Jul 2026 14:45:23 +0000

Now that you mention it, Claude has had trouble at times with balancing brackets in the elisp I have it write.

Yet I still had the idea that LLMs should be better at lisp than other languages.

A fascinating contradiction, thanks for pointing this out.

New comment by zingar in "An agent in 100 lines of Lisp"

zingar — Sun, 12 Jul 2026 14:41:49 +0000

I haven’t seen an LLM generate syntactically invalid code in any language in … a year? So I don’t know if “more likely to be syntactically valid” is a good enough selling point.

But maybe I’m interpreting you too narrowly?

New comment by zingar in "Learning to code is still worthwhile"

zingar — Tue, 07 Jul 2026 09:31:11 +0000

The 1500 line react component that my unsupervised agentic coding side project produced says that it can get worse than we have now.

New comment by zingar in "I built a GPU back end for Emacs"

zingar — Tue, 30 Jun 2026 21:51:29 +0000

org-gcal … bit of a pain getting the Google API config right but so far so good.

New comment by zingar in "Qwen 3.6 27B is the sweet spot for local development"

zingar — Mon, 29 Jun 2026 19:21:06 +0000

Where does “big model highly quantized” start getting worse than “smaller model less quantized”? Is there a general formula or is it just trial and error?

New comment by zingar in "I built a GPU back end for Emacs"

zingar — Fri, 26 Jun 2026 14:23:39 +0000

I fetch my google calendar every few minutes to get everything into my agenda. The API request is async, but writing to the calendar file and some additional processing made Emacs hang for 10 seconds at a time. The LLM-inspired solution was to spawn entire new emacs processes to do the work in the background. It's pretty cool that it works, but it feels like it shouldn't - and wouldn't with 2+ threads - have been that complicated.

New comment by zingar in "Everyone suddenly sells themselves as "AI-native" on LinkedIn"

zingar — Fri, 26 Jun 2026 09:43:24 +0000

This post is a breath of pithy fresh air. A small point made with few words that adds something worthwhile to the conversation.

On topic: maybe I live in a bubble but I'm surprised how many people on LinkedIn expose far behind the curve they are by talking about MCP or RAG or even prompt engineering as if it's a suddenly-new discovery.

It took two weeks to make Claude's "overnight solution" for flaky tests useful

zingar — Fri, 26 Jun 2026 09:40:59 +0000

Article URL: https://thoughtbot.com/blog/what-it-took-to-use-this-overnight-ai-solution

Comments URL: https://news.ycombinator.com/item?id=48684483

Points: 2

# Comments: 1

New comment by zingar in "I rewrote PostHog's SQL parser, 70x faster, while barely looking at the code"

zingar — Wed, 24 Jun 2026 21:56:28 +0000

This must the most compelling look I’ve seen at how software might work with LLMs doing a ton of heavy lifting.

There’s something kind of amazing here in that having read about property based testing I’m pretty confident I could apply it if I had a good use case.

New comment by zingar in "The minimum viable unit of saleable software"

zingar — Tue, 23 Jun 2026 06:18:09 +0000

This is great advice that AI (successfully) tempts me into ignoring.

New comment by zingar in "Did my old job only exist because of fraud?"

zingar — Mon, 22 Jun 2026 14:19:44 +0000

What happened that made you switch away from contracting?

New comment by zingar in "There is minimal downside to switching to open models"

zingar — Mon, 22 Jun 2026 07:24:36 +0000

Yep, this was an issue long before Trump. They’ve just amped up the scale and stopped bothering with the deceit that they know doesn’t bother Americans.

New comment by zingar in "The minimum viable unit of saleable software"

zingar — Mon, 22 Jun 2026 07:18:48 +0000

To be clear these projects made it way further than they could have without AI. But any blocker that takes me out of the flow can easily become the thing that ends it. Not even necessarily because it’s a difficult problem, but just because I’m no longer getting that AI high.

New comment by zingar in "The anatomy of an AI-native org"

zingar — Mon, 22 Jun 2026 07:14:25 +0000

The “old normal” described in this article sounds hellish. This sounds like all the worst practices that need to be drummed out of people who arrive not knowing what effective engineering looks like.

There’s no loss if all of this changes dramatically, there’s plenty of real work to do.

But honest question: where is this normal?

New comment by zingar in "The minimum viable unit of saleable software"

zingar — Sun, 21 Jun 2026 19:04:49 +0000

I have multiple side projects that I would never have contemplated building before but whose utility now exceeds the much lower cost to build.

I got a few weeks in to each and then stalled on all of them because the effort and motivation required to extend beyond the crazed early days _is_ still more than the utility I get.

In a professional context, paying someone for software to do something outside my core domain is still the practical option compared to the motivation and effort needed to maintain another dependency.

New comment by zingar in "Prefer duplication over the wrong abstraction (2016)"

zingar — Sun, 21 Jun 2026 18:15:57 +0000

What’s the difference between a pattern and an abstraction?