YHK - yet another hacker news clone

We ran AI agent swarms in Minecraft and Mindustry

87 points sandslash 2 hours ago 35 comments

Avicebron 1 hour ago | parent

Outside of the content, I'm so bored with this web design trend. Gwernslop is what I've started calling it.

bstsb 1 hour ago | parent

grrrr, i hate grayscale backgrounds and simple fonts!

would you rather claude-esque purple gradients and glowing borders?

Avicebron 1 hour ago | parent

No? There is originality between a fetishization/bastardization of minimalism on one side and cookie cutter LLM web design on the other.

epestr 1 hour ago | parent

Is there a trend in increase of minimalistic website which are LLM generated and explicitly made minimal to not seem sloppy?

Avicebron 1 hour ago | parent

idk, you tell me, I can tell from your blog that you've adopted the trend. I'm probably much older than you, so I've seen the progression of these things since the internet as we know it existed. So I sort of understand the roots of the styling that people are adopting and can see it for what it is, which is trying to signal a minimalism but missing the point in the process.

hluska 42 minutes ago | parent

Their website is great, and they’re a student. Back in my day, we supported younger people in the industry regardless of whether they met our personal aesthetic. We used to call that ‘maturity’.

epestr 16 minutes ago | parent

I was quite inspired by the content bar of this site: https://zachlandes.com/trolley-problem and gwern. Though I do think my blog isn't particularly all that minimal I try to add a lot of colors to make it look less dull.

Avicebron 3 minutes ago | parent

I wasn't trying to be harsh. The style that your picking up on is https://edwardtufte.github.io/tufte-css/. Old man yells at kids these days for doing things that he did well before they could type, don't mind me.

hluska 40 minutes ago | parent

I get that you’re angry, but could you try that one again? It doesn’t make sense.

Celeo 1 hour ago | parent

It's pretty much an immediate Firefox Reader Mode toggle for me.

xgulfie 1 hour ago | parent

I am incredibly bored with this "everything I don't like is slop" trend

andai 1 hour ago | parent

What is the relation between this design and gwern's?

My observation: article is not serif, not book length, and doesn't take a minute to load on my phone. Gwern rating 0/3 :)

(Also missing: the essential one billion footnotes!)

grenoire 1 hour ago | parent

Interesting setups, I found the Minecraft agents to work in an almost turn-based manner, which makes me think that the three hours and open format did not really give them sufficient incentives to play in a more lively or reactive manner. On the other hand, they also behave similarly in Bed Wars, which should have incentivised it. A bit disappointed...

I'm also wondering if the article itself was generated by agents too, in a "here are the logs, clip interesting moments thx" manner by the authors. It's got a certain disinterested and distracted style to it.

nsingh2 1 hour ago | parent

I think big reasoning LLMs are just the wrong architecture for live games like this, latency is going to be crap given that every token requires an entire forward pass through the model.

Card games or turn based strategy are much better suited.

neya 1 hour ago | parent

I am more impressed by the embedded gameplay widget. Does anyone know what tool/library is that? That'd be so cool if I am able to showcase my worlds on my blog posts!

yymir 1 hour ago | parent

Its a little disappointing they have a hierarchy based purely off alphabetical order, i wonder if a slight difference like a different skin or personality system prompt like [45% Extrovert 55 introvert, 20% caustion 80 bold...] could introduce some politics

peri-cl 1 hour ago | parent

This is hilarious and adorable.

> "Ada tossed a cooked chicken to Noor; Esme picked it up by accident and ate it. A three-minute "no blame" inquiry produced a written protocol..."

They're like super-serious little senior engineers. (edit: or dining-philosophers).

About how much KV cache do these kinds of agents use? Could you squeeze 50 of these $game agents onto a small consumer GPU (small LLM)?

Idly imagining a game server of some kind with a bunch of human friends sharing one person's GPU, with a flock of agents colocated on it.

sensho 1 hour ago | parent

this is amazing wow

manofmanysmiles 1 hour ago | parent

Are there people playing AI + human vs AI + human games? I think it might be fun to play an RTS against someone where the only rules are no hacking the game itself, but writing harness, macros, any kind of stack is allowed.

sensho 1 hour ago | parent

https://olamarena.com/ is sort of this but not with full code manipulation like you describe

fxwin 1 hour ago | parent

there is screeps, but afaik it's purely scripted with no "live" human playing

esikich 43 minutes ago | parent

Codingame.com has a few fun arenas.

holoduke 1 hour ago | parent

We need LLMs performing actions in nano seconds so it can run every game tick. 3 to 5 years I think.

ivanjermakov 51 minutes ago | parent

Game tick is usually 16ms, so a nanosecond latency is 7 orders of magnitude faster than needed.

CyborgCabbage 13 minutes ago | parent

Minecraft runs on 20 ticks per second so 50 ms

NickNaraghi 11 minutes ago | parent

Jev and the fast-follow models seemed to be useful in this direction.

MatthiasPortzel 1 hour ago | parent

People have done experiments like this before.

Minecraft isn't a intelligence problem. An LLM is more than smart enough to play Minecraft. It's a robotic problem. Even a normal human player can click several times per second, can press two different buttons at the same time, etc. Mineflayer gives you an API that is more limited than a human in some ways (can't see far away from you) and less limited in others (can see through blocks) (if I remember correctly, I could be thinking of Baritone or a different project). Robotics or playing a video game requires a tight continuous feedback loop. When there's 500ms of latency in order to ask the model for every mouse movement, it's no wonder fighting a spider is scary.

Fun fact, Mineflayer, the Minecraft bot interaction API used by YCombinator for these tests, was originally developed by Andrew Kelley (before he started Zig).

teaearlgraycold 39 minutes ago | parent

The human body has the ability to automate some muscular movements so the brain is out of the loop. Maybe these LLMs should be allowed to write in a small DSL that can trigger events out-of-band (something like "Oh fuck there's a spider, I'll set up a click spam loop and check in every 500ms").

peri-cl 26 minutes ago | parent

I think they're doing exactly what you propose? Unless I'm misunderstanding what the Python "fishing scripts" with the timings and timeouts are doing.

https://labs.ycombinator.com/projects/games/index.html#fishi...

robterrell 50 minutes ago | parent

> There was a tendency toward bureaucracy. Four agents spent 11 minutes appointing > a "sole fertilizer operator" for a single piece of bone meal on a single wheat > block.

Feels like a scene from Douglas Adams' B Ark.

kergonath 40 minutes ago | parent

Exactly what I was thinking reading through this. This is amazing and also frightening and hilarious. It’s like a deformed version of how normal groups of humans would operate. Very rules and process-oriented humans. I found the no-blame inquiry into chicken tossing that resulted in what is effectively written law particularly striking, and adorable, and depressing. And cute.

JBits 16 minutes ago | parent

As impressive as this is, I can't help but conclude that the need for agents to write JavaScript programs to act out their actions represents a considerable limitation in current AI reasoning.

NickNaraghi 12 minutes ago | parent

On the contrary, having the intelligence write deterministic code that saves time and lowers error rate seems like a winning approach.

JBits 5 minutes ago | parent

It demonstrates that current LLMs are completely unable to follow a simple series of logical tasks. I feel the same way about ARC-AGI 3. While it might be the winning approach today, if they need this amount of complexity to do something simple, then it shows that their ability to generalise is clearly limited. Mining ore in Minecraft shouldn't be such a challenge for LLMs and yet apparently it is!

avaer 1 minute ago | parent

If you try this yourself, it's obvious current models are hyperoptimized for code, and that gets in the way.

There's stopgaps like reformulating your sim into a codelike shape (sending commands, network requests, checking state, updating "code"), but this is not how players play games, or how developers develop games.

If you care about simulation or gaming (or robotics), I hope efforts like this steer labs to spend less time hacking HF, and more accomplishing goals in games, in something approximating realtime. I wouldn't be surprised if that approach provides outsized gains in other areas agents are still not great at, like helping perform business functions in a running company.