Hacker News: Dzugaru

New comment by Dzugaru in "Yes, and"

Dzugaru — Fri, 09 Oct 2026 10:50:56 +0000

Have you tried creating something that doesnt have HUNDREDS of existing implementations on the Web already?

New comment by Dzugaru in "EVE Online's Carbon engine is now open source: Fenris Creations explains why"

Dzugaru — Wed, 08 Jul 2026 11:51:56 +0000

Depends on the way you play can be a time sink, or session-like game. It is extremely deep and complex to learn from scratch though.

I've made some of the best friends playing it when I had time, friendship formed out of high stakes in this game (you regularly lose hours of grind or real money if you pay for the game - in seconds) and respect you have for each other skill.

New comment by Dzugaru in "An entire Herculaneum scroll has been read for the first time"

Dzugaru — Thu, 25 Jun 2026 17:57:44 +0000

Outstanding work! I've participated in the challenge, but didn't get far. One of the questions I had at the time was - if I'm going to use ML to detect ink, could it invent hallucinated letters, or even parts of text, and how to prevent that?

New comment by Dzugaru in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

Dzugaru — Wed, 27 May 2026 10:43:25 +0000

How much time do you lose when doing things like "verify plan with a second clean agent" instead of just reading and fixing it yourself in 5 min? How much understanding do you lose? How do you manage to treat it "as an engineer" where it's clearly not there yet? How much time do you lose when it makes almost the same mistake, invents stuff or tries to gaslight you over and over? What about blood pressure?

New comment by Dzugaru in "Frontier AI has broken the open CTF format"

Dzugaru — Sun, 17 May 2026 12:57:34 +0000

I did vibe code jam 59 entry with friends, the spirit of the rules there's a lot more lax. We didn't even get to top 100, but that's mostly due to gamedesign errors, not tech. This is the first entry in years which was vibecoded 100%, and I have very mixed feelings about it. It's no doubt anymore - 1.5x-2x speedup, which makes not using it (if allowed) a complete no-go. But psychologically it's tough losing control, and changing workflow to managerial one substantially, it diminishes the craft.

New comment by Dzugaru in "Frontier AI has broken the open CTF format"

Dzugaru — Sat, 16 May 2026 22:49:27 +0000

It's not only CTFs. I strongly believe being a programmer at a gamejam like Ludum Dare, or hackathons is pretty much over.

New comment by Dzugaru in "Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?"

Dzugaru — Sat, 31 Jan 2026 19:53:07 +0000

But how is that less work and allows you to do that in Disneyland with your kids? For me, personally, there is little difference between "speccing out everything in excruciating detail in spec docs" and "writing actual implementation in high-level code". Speccing in detail requires deep thought, whiteboard, experimentation etc. All of this cannot be done in Disneyland, and no AI can do this at good level (that's why you "spec out everything in detail", create "beads" and so on?)

New comment by Dzugaru in "Vibe Code Warning – A personal casestudy"

Dzugaru — Tue, 11 Nov 2025 19:05:52 +0000

This is so far from an absolute worst-case scenario.

You could have a codebase subtly broken on so many levels that you cannot fix it without starting from scratch - losing months.

You could slowly lose your ability to think and judge.

New comment by Dzugaru in "A high schooler writes about AI tools in the classroom"

Dzugaru — Thu, 04 Sep 2025 22:56:27 +0000

I have a feeling this is somehow different. The tool is broad enough, that I don't have to think myself in a wide variety of tasks, not just one. Which hurts my intelligence way more.

New comment by Dzugaru in "OpenAI Progress"

Dzugaru — Sun, 17 Aug 2025 10:45:04 +0000

There is no hidden state in a recurrent nets sense. Each new token just has all the previous tokens and that’s it.

New comment by Dzugaru in "Gemini with Deep Think achieves gold-medal standard at the IMO"

Dzugaru — Mon, 21 Jul 2025 20:19:50 +0000

Most critical piece of information I couldn’t find is - how many shot was this?

Could it understand the solution is correct by itself (one-shot)? Or did it have just great math intuition and knowledge? How the solutions were validated if it was 10-100 shot?

New comment by Dzugaru in "Measuring the impact of AI on experienced open-source developer productivity"

Dzugaru — Thu, 10 Jul 2025 20:52:36 +0000

This is really interesting, because I do gamejams from time to time - and I try every time to make it work, but I'm still quite a lot faster doing stuff myself.

This is visible under extreme time pressure of producing a working game in 72 hours (our team scores consistenly top 100 in Ludum Dare which is a somewhat high standard).

We use a popular Unity game engine all LLMs have wealth of experience (as in game development in general), but the output is 80% so strangely "almost correct but not usable" that I cannot take the luxury of letting it figure it out, and use it as fancy autocomplete. And I also still check docs and Stackoverflow-style forums a lot, because of stuff it plainly mades up.

One of the reasons is maybe our game mechanics often is a bit off the beaten road, though the last game we made was literally a platformer with rope physics (LLM could not produce a good idea how to make stable and simple rope physics under our constraints codeable in 3 hours time).

New comment by Dzugaru in "Seven replies to the viral Apple reasoning paper and why they fall short"

Dzugaru — Sun, 15 Jun 2025 10:31:33 +0000

> just as humans shouldn’t serve as calculators

But they definitely could and were [0]. You just employ multiple, and cross check - with the ability of every single one to also double check and correct errors.

LLMs cannot double check, and multiples won't really help (I suspect ultimately for the same reason - exponential multiplication of errors [1])

[0] https://en.wikipedia.org/wiki/Computer_(occupation)

[1] https://www.tobyord.com/writing/half-life

New comment by Dzugaru in "What was Radiant AI, anyway?"

Dzugaru — Sat, 07 Jun 2025 14:50:02 +0000

Not possible, because can't be guardrailed with 100% accuracy. You'll ask it something outside of the Warcraft world (e.g. US politics), and it'll happily oblige. I imagine NPCs will generate really weird immersion breaking stuff even if you cannot freeform interact with them anyway.

Not to mention the current token cost.

New comment by Dzugaru in "AI predicts earthquakes with unprecedented accuracy"

Dzugaru — Tue, 27 Aug 2024 07:24:11 +0000

Used to live near Japan, in a 5-story concrete building. We had so many earthquakes, the things were getting thrown off the shelves multiple times a year. There is nowhere to leave for a week. And there is a very slim chance anything would collapse, because the buildings are specifically built to withstand up to around 9 richter.

New comment by Dzugaru in ""Superintelligence" 10 years later"

Dzugaru — Thu, 04 Jul 2024 10:53:40 +0000

If we can create a human-level intelligence in the computer - it would already be superintelligence. No human on Earth is capable of reading and remembering Internet scale corpus of data, or doing math at GHz speeds, etc.

New comment by Dzugaru in ""The Door Problem" (2014)"

Dzugaru — Fri, 14 Jun 2024 13:33:19 +0000

Start with game jams. When you're constrained to make a complete game in 48/72 hours, suddenly you start to understand what's important and what's not. Granted, I haven't done any doors in my jam games yet =)

New comment by Dzugaru in "The importance of making games during a game engine's development"

Dzugaru — Tue, 27 Feb 2024 09:46:55 +0000

There are far more games that were made with Unity, not Unreal, I would even say an order of magnitude more. So I don't really get your point? Unity is vastly easier to jump on, so a lot more people actually make games and test things (not knowing the quirks of the engine inside out, like a game engine developer would).

Ask HN: Books about security/wargames/CTFs?

Dzugaru — Sat, 03 Jun 2023 10:30:06 +0000

I've enjoyed playing OverTheWire's Bandit [0] immensely. But many concepts were unfamiliar, and I had to guess how the things work. I want to get more thorough understanding of infosec, possible attacks (in games and in the wild), maybe even real life stories - and also something I can read on my commute.

[0] https://overthewire.org/wargames/bandit/

Comments URL: https://news.ycombinator.com/item?id=36175371

Points: 1

# Comments: 0

New comment by Dzugaru in "Make your CLI demos a breeze with zero stress and zero mistakes"

Dzugaru — Wed, 05 Apr 2023 10:58:47 +0000

He actually mentions the tool [0] that has all of this, in the end. It records your screen and compiles a demo that runs in any browser by the looks of it.

[0] https://www.terminalizer.com