tripleee

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.

> 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?

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.

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

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.

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.

In this case you could give it its own SSH key, and only allow that key to access what you want. I actually do that, it doesn't share my own SSH key. It also has its own Github account instead of getting access to mine.

For access to services, most allow tokens to be scoped to only allow the things you want.

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?

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?

I thoroughly sandbox agents to their own physical machine, and they don't have access to anything that would ruin me.

Why can't LLMs be used for long-term care of a software project?

This seems to be more on the tool-wielder than the tool.

Linux itself is receiving LLM-assisted code (a quick search saying 20% at the moment, although I don't know how accurate that is)

Patents and copyright are there to allow businesses to recoup investment in R&D

The end result of what you're talking about isn't that the innovator will be copied and consumers will benefit.. it's that the innovator will no longer exist and no-one will benefit.

I'd love to hear you justify it

There has been plenty of crap released in the past, and even in the AI age we should be able to look at the same signals to filter through it today.

Should an AI have expanded it to 3 paragraphs to say the same thing?

> today it offered me “Finances” which would allow me to connect my financial data

Did you though?

I don't really think looking at it through the lens of tobacco works. Parents giving their children tobacco and heroin aren't a thing. In reality many are self-motivated to give them a tablet for their own benefit, nothing much to do with the kid

Screens or tablets aren't the harmful drug in this situation, they're the needle. A needle that can contain medicine or heroin. The harm is from specific apps and social media. A device can be locked down. You can control what it's able to do and how much. I've used screens to teach myself a language to fluency, a hell of a lot about software development, and countless other things.

Would you object to a tablet that could only access Khan Academy, Openstax and Udemy? What about if we added on a 20 minute allowance of social media? I haven't looked super deep into the Amazon device much but it seems this is the direction they're heading with the parental dashboard

"Educational content has to come first. Your child completes reading or learning goals in Kids+ and educational apps before entertainment apps unlock"

I mean obviously kids are going to try to game the system to get to what they want.. but it seems like a reasonable path to test, and it doesn't require trying to turn every bad parent into a good one, or do something outlandish like ban tablets

I don't see what banning it actually accomplishes unless we totally ban tablets altogether. From the way I see it, it's the parents who are choosing to give their kids tablets in order to make their own parenting job easier. Am I wrong there? What do you ban to stop that happening?

The net harm result really only changes because the scope and numbers differ. I don't think I've ever met anyone who actually allows their kids to smoke, I see a lot who give them tablets though.

If we instead imagine a world where parents allowed, even encouraged 60% of children to smoke, and there was no clear route to outright stopping them, giving them at least a better alternative that doesn't hurt them as much would be worth considering

The existence of them, yeah. I don't think it's so clear cut that it'd be a net increase in harm. Advertising I'm not so sure about, but as for the mere existence of them:

Group A is going to smoke regardless, having a healthier product reduces harm

Group B is never going to smoke no matter what's on offer

I mean uranium can be a hazard to people around you, so I don't think that's an equivalent scenario.

Drugs could be a good analogy as it (mostly) affects yourself. A safe route for people to buy those would fix the #1 leading cause of death of young adults in the US today (fentanyl)

Do you have a strong argument against them?

The group of parents who let their kids smoke might get those instead, improving their health

The parents who don't allow it would never consider them

I suppose it depends how many of group 2 could be converted to 1 if they were "low tar!".. my intuition is close to zero

Reality is that telling future bad parents not to have kids isn't going to stop them having kids, even if you say please

The demand was for transportation, not any specific product.

Amazon's target market here, wants to parent their kids without parenting their kids. Whether that's a TV with cartoons 20 years ago, a tablet 5 years ago, or a "digital pacifier" today nothing has changed. It's just being fulfilled differently.

My point is that the responsibility is on parents, not companies who will inevitably get the blame and nothing will change. See the other commenter here who said their kids don't even own a tablet.

So.. stop producing smartphones / tablets? TVs? What's your other option?

Demand for products comes from the consumer, not the producer. This trend happened a long time ago, with parents giving their kids a tablet to avoid actually parenting.

Maybe it's making the best of bad parents

Oh but why do they need a high salary when AI gives us free software? /s