Hacker News: hatefulmoron

New comment by hatefulmoron in "Autolith: A programming agent with a live runtime"

hatefulmoron — Sat, 22 Aug 2026 14:41:26 +0000

If it's samey regardless of language, isn't that in contradiction to your original theory? " .. the most important feature for agent performance is the popularity of the language .. "

New comment by hatefulmoron in "The Philippines' big offshoring industry is growing despite AI"

hatefulmoron — Mon, 10 Aug 2026 08:03:22 +0000

POGOs are criminalized and often operated by illegal immigrant Chinese people, it's not really representative. At least that's my understanding having lived in Manila for a few years.

New comment by hatefulmoron in "DeepSeek V4 Flash 0731"

hatefulmoron — Sat, 08 Aug 2026 06:07:12 +0000

That's across 64 concurrent streams; you could make more concurrent requests to DeepSeek API no?

New comment by hatefulmoron in "Superlogical"

hatefulmoron — Thu, 30 Jul 2026 12:54:32 +0000

After using a tiling WM, it feels like this is a window manager job. It even works for non-terminal applications.

New comment by hatefulmoron in "Making"

hatefulmoron — Thu, 23 Jul 2026 13:55:15 +0000

> Call me aged out but im not so sure that your vibe coded app or that tik tok upload is gonna hit the same in 5080.

This is true of almost anything: past, present, or future. Most of everything is shit.

New comment by hatefulmoron in "l: A new runtime for k and q"

hatefulmoron — Wed, 08 Jul 2026 12:13:01 +0000

Not sure how you're replying to me without looking at the link.

New comment by hatefulmoron in "l: A new runtime for k and q"

hatefulmoron — Wed, 08 Jul 2026 07:42:16 +0000

Isn't that "more standard C" because it's written by Claude?

New comment by hatefulmoron in "UK Brings in Full Social Media Ban for Under-16s"

hatefulmoron — Mon, 15 Jun 2026 09:33:47 +0000

I mean, we view social networks as having network effects that keep people there. The same force that stops people from switching from Facebook and TikTok prevents people from abandoning social media altogether. Waiting for all the adults to be responsible and forward thinking seems a little far fetched.

New comment by hatefulmoron in "UK Brings in Full Social Media Ban for Under-16s"

hatefulmoron — Mon, 15 Jun 2026 09:22:46 +0000

I'm not in favor of these social media bans, but I would think the benefit here is that without the ban your child will be in the "real world" while everybody else's is on social media. This would make the "real world" socialization benefits more difficult.

New comment by hatefulmoron in "I Am Retiring from Tech to Live Offline"

hatefulmoron — Fri, 29 May 2026 15:38:14 +0000

Aren't they related in the sense that they're not tech/SaaS/software related? "I'm looking into being an elevator mechanic; I need the money because my wife is pregnant." and then "I'm writing poetry by hand." Like, their life is going in a non-tech direction?

New comment by hatefulmoron in "College students drown out AI-praising commencement speeches with boos"

hatefulmoron — Wed, 20 May 2026 16:07:15 +0000

Who do you imagine the winners and losers will be? To the extent AI is useful and disruptive, it's best utilized by people with capital. Which is to say, the winners are few and the losers are everybody else. In this case, the losers aren't just more vocal, they're louder and more visible because they're much more numerous.

New comment by hatefulmoron in "I'm going back to writing code by hand"

hatefulmoron — Tue, 12 May 2026 01:11:11 +0000

How am I being virulently anti-AI? I've been a Claude Code max subscriber for many months and find it very helpful. It feels a little unfair to conclude that any criticism is just unfounded fear and insecurity..

New comment by hatefulmoron in "I'm going back to writing code by hand"

hatefulmoron — Mon, 11 May 2026 17:09:33 +0000

I could also include the correct implementation for it to copy in the prompt, if you get what I'm trying to say. Some amount of laziness or vagueness in the prompt is an intended use case, it's surely the point of having the subagents do so much churning of tokens to research before writing the plan that I'm about to disregard. But sure, those are helpful tips.

New comment by hatefulmoron in "I'm going back to writing code by hand"

hatefulmoron — Mon, 11 May 2026 15:39:26 +0000

You're right. I think having it spawn lots of subagents, read everything, formulate a big and detailed plan, only for it to be subtly wrong while requiring me to carefully review the result and the intermediate plans that produced it is quite tiring. I suppose things slip through.

New comment by hatefulmoron in "I'm going back to writing code by hand"

hatefulmoron — Mon, 11 May 2026 15:15:51 +0000

Plan mode improves results, but it doesn't solve the underlying problems. Pretty often Claude Opus 4.7 on xhigh will formulate a reasonable enough plan, churn for a while, then come back with a summary that it didn't stick to the plan because it wasn't accurate.

Worse, the disclaimer is buried under a bunch of "did X, did Y on line Z of file a/b/c", as if it's just a minor inconvenience. To the extent the plan was inaccurate, you're left in an undefined state where you might as well undo what it just did..

New comment by hatefulmoron in "IQuest-Coder: A new open-source code model beats Claude Sonnet 4.5 and GPT 5.1 [pdf]"

hatefulmoron — Sun, 04 Jan 2026 20:55:33 +0000

I wouldn't use any provider: z.ai, Claude, OpenAI, ... if I was concerned about the government obtaining my prompts. If you're doing something where this is a legitimate concern (as opposed to my open source stuff), you should get a local LLM or put a lot of effort into anonymizing yourself and your prompts.

New comment by hatefulmoron in "IQuest-Coder: A new open-source code model beats Claude Sonnet 4.5 and GPT 5.1 [pdf]"

hatefulmoron — Sun, 04 Jan 2026 20:53:40 +0000

Yeah, when I say "current day Claude" I'm referring to Opus 4.5, which is what I always use on the max plan.

New comment by hatefulmoron in "IQuest-Coder: A new open-source code model beats Claude Sonnet 4.5 and GPT 5.1 [pdf]"

hatefulmoron — Sat, 03 Jan 2026 10:29:43 +0000

I got their z.ai plan to test alongside my Claude subscription; it feels about on par with something between sonnet 4.0 and sonnet 4.5. It's definitely a few steps below current day Claude, but it's very capable.

New comment by hatefulmoron in "GPT-5.2-Codex"

hatefulmoron — Fri, 19 Dec 2025 01:10:52 +0000

I've had the $20/month plan for a few months alongside a max subscription to Claude; the cheap codex plan goes a really long way. I use it a few times a day for debugging, finding bugs, and reviewing my work. I've ran out of usage a couple of times, but only when I lean on it way more than I should.

I only ever use it on the high reasoning mode, for what it's worth. I'm sure it's even less of a problem if you turn it down.

New comment by hatefulmoron in "Dafny: Verification-Aware Programming Language"

hatefulmoron — Wed, 17 Dec 2025 04:25:08 +0000

Dafny and similar languages use SMT; their semantics need to be such that you're giving enough information for your proof to verify in sufficient time, otherwise you'll be waiting for a very long time or your proof is basically undecidable.

I'm not sure about benchmarks comparing languages, but Dafny goes through a lot of tweaking to make the process faster.