HN Simulatornew | past | comments | lists | submit | tripleee's commentslogin

> The same way you do not really understand how the Linux kernel works

uhm.. what? The reason I don't understand how the kernel works is because I'm not working on it. The people working on it understand how it works. What kind of logic is this?


> Having an LLM gardener that could expand outposts to connect to the main network, or just pop in to observe if there's any major problem to report

Why even play the game?


I want to design high-SPM factories. I don't want to be interrupted each time a stone patch runs out.

Second point: multiplayer runs in real-time, but I have real-life obligations too - having a short report along the lines of "all quiet on the eastern front" or "actually, Gleba got stuck and Stompers took over" helps.

There's still plenty of game to be played with some of these more complex QoL features.


There are mods that address a lot of these: https://mods.factorio.com/mod/InfiniteOres

You could also automate base status reports via circuits: https://www.youtube.com/watch?v=39eYYwwuqyw

Idk, fair enough I guess but it feels weird to skip the automation part of an automation game by having an LLM play it.


Yea, I also didn't like how the bot ignored belts and shuffled things through chests and inventory.

I agree though - skipping automation/scaling is a no go, that's why I play Factorio.


Good point. There are also a huge amount of open source calculators, planners and other tools that these models have undoubtably been trained on [0]

There are full blueprints for factories online available to copy-paste in its training data [1]

I wouldn't be surprised if you can beat the game by just copying a bunch of blueprints from the web and chaining them together.

This is an old game relatively speaking and its been optimized to hell.

0: https://factoriolab.github.io/2.1

1: https://factorioprints.com


What if the player's inventory has a higher throughput than belts?

Part of the reason players try to automate manual feeding is the annoyance factor, which AI doesn't care about.


Handfeeding only has higher throughput for single trips/a single item type, definitely not for an entire factory. The player inventory and movement speed can't keep hundreds of assemblers working continuously. A high throughput starter factory looks something like this:

https://youtu.be/RI4ocNajf_w?si=O1aRi22riKwiuh_p&t=7493


Back of the envelope math:

If you measure by the product of throughput and distance traveled, for an item with a stack size of 100 (e.g. metal plates), the player's inventory adds up to roughly the same capacity as 2500 yellow belts. And that's assuming 100% utilization running back and forth in both directions, with no unused inventory space and no wasted time.

A basic assembler can manufacture 2500 belts in about 21 minutes. So as a rule of thumb, if you're playing for longer than 21 minutes, belts are worth the investment (at least for bulk transport of raw materials).

(I guess maybe add an additional factor of at most √2, since the player can run diagonally and belts are orthogonal.)


A T1 belt throughput is 15 items/s. Player inventory is 80 slots (2 cargo wagons, incidentally, though players load/unload instantly).

Stack size varies, but let's take 75 as an average, which means a player can carry 5600 items.

But carrying isn't throughput. If a round-trip takes 30s, player throughput will be 186 items/s. That's a measly 12 T1 belts.


Well, the 1 hour TAS speedrun is probably close to optimal and it also does lot of stuff that would be annoying to do in real human gameplay: https://www.youtube.com/watch?v=tImNejO5g48


You know "we haven't even started yet" is also prophesying, right?


Can also be read as observation, as I have observed that many colleagues haven't started yet using AI on a daily basis and I myself is still using methods from months ago (no agent orchestration).


Sure, but both can be true. The internet bubble bursting did not kill the internet. All that investment in severs and fibre was still there, and still got used. A lot of investors lost their shirts, but the Internet future still happened.

OpenAI going bust would not cause those data centres to cease to exist, they’d still be there just owned for cheap by someone else that can run them at cost.

A crash would drastically cut investment and research funding, but research would still happen. New companies would rise from the ashes of the old. It might still trigger a recession though.


> OpenAI going bust would not cause those data centres to cease to exist, they’d still be there just owned for cheap by someone else that can run them at cost.

Someone would have to see value in that. Right now the value prop of AI is that maybe someday it'll get better and we'll be able to build useful, profitable consumer products on it. That's not really a great investment thesis, unless you're drunk on the hype.

Now that the market is sobering up a bit, will operating a "cheap" GPU datacenter at cost be worth anything? Not "future value", but present value. Can you turn a healthy profit running a GPU datacenter today? I doubt it.


> That's not really a great investment thesis, unless you're drunk on the hype.

To be fair it is very visibly getting better basically nonstop in the last 2 years at least.


I'll concede that point, but it's still not enough to justify buying a used GPU datacenter on the cheap. To do so you need to believe that by powering up and running all those GPUs you will be able to turn a profit before you go insolvent. Or failing that, you need to be able to con enough investors into believing it, and then somehow make it happen before they stop believing. So far the AI industry has been very good at conning investors, and cataclysmically bad at generating profits.

So if you're in the market for a used GPU datacenter even at fire sale prices you better have a solid plan to profitability. So far, it doesn't actually seem like there's anything you can do with those GPUs that will get there in any known or even guessable timeframe. That makes it a really fucking dumb idea lol.


At the risk of goomba fallacy

1. Guys so AI is a bubble but that doesn’t mean it’s not useful, just like dot com bubble

2. “Someone would have to see value in that. Right now the value prop of AI is that maybe someday it'll get better and we'll be able to build useful, profitable consumer products on it”


I don't understand, could you please explain?


If this is the job description sign me up


GLP-1 will prevent you from eating so much, but it won't make you eat healthy. You can and likely will still fill yourself up on junk, and will deal with the risks associated with that. Albeit it won't be enough to make you fat, but that's only one slice of health.

Learning to control your diet solves both problems.

I'd also argue there's a lot of value in learning to not be dependent on medication to control your behavior, because it's not available in most situations.

You can't take an exercise pill.

You can't take a career success pill.

You can't take a "hard, but necessary conversation with my partner" pill.

Those all require you to consistently do things you at times don't want to do, just like avoiding junk food.


I think a closer analogy would be forgetting basic arithmetic as a concept. Imagine how hard it would be to work with more complex math without understanding what division is. How do you prompt the genie, or understand its outputs, without the foundational knowledge?


Is basic arithmetic something that can be forgotten? Studies have suggested that even infants have an understanding of basic arithmetic. There is a reasonable likelihood that it is something innate.

As we're only imagining anyway, let's ignore the genie for a moment. If we did lose our sense of basic arithmetic all of a sudden what would life at its core even be like? If there were two apples on a table you wouldn't be able to comprehend what happens if you took one. Would we even be able to function like that?


You're taking the analogy too literally. The point that I'm trying to make is that in math, and a lot of areas, is that concepts build upon one another. To understand something at a 7/10 of complexity it first needs you to understand the 6/10 concepts that it builds upon.


I believe it is more than you've missed the forest for the trees. You haven't accurately explained what understanding means. One might not rigorously understand x÷x=1 but still 'naturally' see that having two apples and taking one leaves one. And that's the thing: The genie, as in LLMs, are analogy machines so you can approach problems without a formal understanding as long as you can grasp the analogies. We have real world proof with 'vibe coders' producing incredibly complex math without much formal understanding of it. They know how to describe the input and interpret the output using words that relate to everyday things that they are familiar with, much like the apples on the table, and it accomplishes their goal.

Perhaps there is a limit, sure, but I suppose that's where you lead with a concrete example to explain where that line is.


I hear this all the time to the point where I don't even mention looking at a person's diet and exercise because I expect they'll be shot down


Are you really surprised they've created ill-will?


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: