Hacker News: movedx01

New comment by movedx01 in "Claude for Creative Work"

movedx01 — Wed, 29 Apr 2026 08:48:19 +0000

> coming soon

The developers are literally on the bleeding edge here, it might be the most developed of the AI use cases right now. The most advanced tooling for LLMs revolves around SWE work, there are multiple prolific benchmarks that the labs are actively targeting in this area, and new ones are being built, whole product categories being spawned, software companies bleeding money for tokens.

It's the other professions that are to follow once the training data is in place to go reach for their livelihoods. SWEs got the early taste of what is coming. And the blender news is exactly that.

New comment by movedx01 in "Average is all you need"

movedx01 — Fri, 17 Apr 2026 13:31:15 +0000

Average is only a tombstone of someone having failed to do better. And settling for average means pulling down.

When it comes to bs dashboard where "average is all you need", maybe the "better than average" result would be asking yourself if it's even worth doing in the first place?

New comment by movedx01 in "Average is all you need"

movedx01 — Fri, 17 Apr 2026 13:27:01 +0000

Probably the same way other models learned to surpass human ability while being bootstrapped from human-level data - using reinforcement learning.

The question is, do we have good enough feedback loops for that, and if not, are we going to find them? I would bet they will be found for a lot of use cases.

New comment by movedx01 in "Ask HN: What Are You Working On? (April 2026)"

movedx01 — Mon, 13 Apr 2026 11:57:18 +0000

I am vibe-porting an old game, Knights & Merchants(actually its Delphi rewrite - KAM Remake) to WASM. It's going well, I even have multiplayer working, will release it publicly at some point.

Learned more about WASM, OPFS, JSPI and other exotic browser stuff more than ever, also learned more about pascal than I ever wanted to, but it's been immensely fun.

New comment by movedx01 in "Thoughts on slowing the fuck down"

movedx01 — Wed, 25 Mar 2026 20:05:40 +0000

Not having a code review process is archaic engineering practice at this point(at any point in history, really), be it for human written or AI written code.

New comment by movedx01 in "LLMs work best when the user defines their acceptance criteria first"

movedx01 — Sat, 07 Mar 2026 09:11:30 +0000

Perhaps the problem is that you RL on one patch a time, failing to capture the overarching long term theme, an architecture change being introduced gradually over many months, that exists in the maintainer’s mental model but not really explicitly in diffs.

New comment by movedx01 in "An autopsy of AI-generated 3D slop"

movedx01 — Thu, 26 Feb 2026 18:49:46 +0000

While at the same other companies have built entire business lines around fixing shit code(probably with more of the same though).

New comment by movedx01 in "Will vibe coding end like the maker movement?"

movedx01 — Thu, 26 Feb 2026 18:38:28 +0000

It doesn't matter, neither of those scenarios makes the effort impressive in this case. The vibe coded thing might even be useful - that does not make it impressive though. Effort does.

New comment by movedx01 in "AI is destroying open source, and it's not even good yet [video]"

movedx01 — Mon, 23 Feb 2026 18:43:43 +0000

Orphaned or as Peter Naur wrote in 1985(https://pages.cs.wisc.edu/~remzi/Naur.pdf), dead programs :)

New comment by movedx01 in "Writing code is cheap now"

movedx01 — Mon, 23 Feb 2026 17:53:39 +0000

Autolands absolutely do exist.

New comment by movedx01 in "How AI is affecting productivity and jobs in Europe"

movedx01 — Thu, 19 Feb 2026 09:55:33 +0000

You know what is an insult? Supermarket on my street putting on display sloppy ads with ramen bowl that has 3 different thickness chopsticks and cartoon characters with scrambled faces. Now that is an insult, because there was a human being doing that job, and I am sure there was a great "productivity boost" related to that change.

I am a heavy AI user myself, and sure as hell I am not putting my foot in that place again.

New comment by movedx01 in "The Human in the Loop"

movedx01 — Thu, 22 Jan 2026 13:12:25 +0000

AI derived piece arguing with another AI derived piece about AI. It's slop all the way down.

New comment by movedx01 in "Getting a Gemini API key is an exercise in frustration"

movedx01 — Thu, 11 Dec 2025 14:39:40 +0000

Is that even possible? Last time I checked it wasn't, while it was possible with OpenAI. Since that moment(early this year) - OpenAI has removed that option and their "Project budget" feature turned from being a hard limit into an email notification.

New comment by movedx01 in "Workday to acquire Pipedream"

movedx01 — Thu, 20 Nov 2025 17:08:39 +0000

Is it the first one priced reasonably and transparently, or am I missing something here?

New comment by movedx01 in "GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search"

movedx01 — Mon, 08 Sep 2025 08:53:12 +0000

Don't forget about the "ChatGPT 5 Pro" too :) which is a bit like Deep Research but not quite?

New comment by movedx01 in "Reverse engineering GitHub Actions cache to make it fast"

movedx01 — Wed, 23 Jul 2025 13:46:44 +0000

Anything for artifacts perhaps? ;) We use external runners(not blacksmith) and had to work around this manually. https://github.com/actions/download-artifact/issues/362#issu...

New comment by movedx01 in "CSS's problems are Tailwind's problems"

movedx01 — Tue, 22 Jul 2025 17:10:12 +0000

Is that true though? Every time i tried to get Sonnet to write out any actually complicated layout/component, I ended up with a novel of classNames with a ton of duplication and useless additions. Those are very hard to spot inside a soup of tailwind classes, whereas I can see them immediately in a nicely laid out stylesheet. This happened extremely often when I tried to iterate with Cursor/CC on the given design, instead of giving up immediately after it failed to one-shot it.

New comment by movedx01 in "Show HN: Pickaxe – A TypeScript library for building AI agents"

movedx01 — Mon, 23 Jun 2025 20:08:51 +0000

This is great, and I keep my fingers crossed for Hatchet!

One use case I imagine is key here is background/async agents, so OpenAI Codex/Jules style, so that's great if I can durably run them with Pickaxe(btw I belive I've read somewhere in temporal docs or some webinar that Codex was built on that ;), but how do I get that real-time and resumable message stream back to the client? The user might reload the page or return after 15 minutes, etc. I wasn't able to think of an elegant way to model this in a distributed system.

New comment by movedx01 in "Remote MCP Support in Claude Code"

movedx01 — Sun, 22 Jun 2025 09:56:28 +0000

That's great! It would be even better if one of the features included in the table was whether given MCP supports OAuth Dynamic Client Registration, which optional in the MCP standard.

New comment by movedx01 in "Phoenix.new – Remote AI Runtime for Phoenix"

movedx01 — Sat, 21 Jun 2025 10:15:37 +0000

anything OAuth