HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Dzugaru

535 karmajoined 10년 전

comments

Dzugaru
·6일 전·discuss
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.
Dzugaru
·19일 전·discuss
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?
Dzugaru
·2개월 전·discuss
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?
Dzugaru
·2개월 전·discuss
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.
Dzugaru
·2개월 전·discuss
It's not only CTFs. I strongly believe being a programmer at a gamejam like Ludum Dare, or hackathons is pretty much over.
Dzugaru
·5개월 전·discuss
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?)
Dzugaru
·8개월 전·discuss
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.
Dzugaru
·10개월 전·discuss
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.
Dzugaru
·11개월 전·discuss
There is no hidden state in a recurrent nets sense. Each new token just has all the previous tokens and that’s it.
Dzugaru
·12개월 전·discuss
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?
Dzugaru
·작년·discuss
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).
Dzugaru
·작년·discuss
> 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
Dzugaru
·작년·discuss
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.