js8

LLM is just a computer program, we have binary code for it. The human brain is not. It would be unethical to even attempt that.

Why is it so surprising? Humans can make compilers that are better coders than they themselves are.

> Obviously this doesn't work on the internet

Not obvious to me. I am generally a fan of Cyberspace manifesto and the free Internet, I think it's great people can reach outside their ingroup and talk to strangers and ostensible enemies.

But, that doesn't mean we should give up physical security, the guarantee that the connecting party comes from a certain physical location (state, company). I think allowing connections from anywhere by default is fundamentally flawed security architecture, for certain things.

Big vs little endian are equivalent up to rotation, which includes permutations.

But it's actually much weaker condition than it looks, because, for example, lot of representations of boolean circuits are equivalent up to linear transformations over Z_2^n.

Anyway, if they truly proven such a theorem you won't find "incompatible" representations of the same thing.

Way to miss the point. Any government can take any share from economy and redistribute it more fairly. There is nothing specific to oil that makes society more equal.

The argument "but Norway has oil" is so tiring. So what, US has a big tech with huge profits. Why can't you have a UBI from ads? Of course you can.

When you get a dollar bill, you can actually tell whether it's from oil or not? I can't..

What's really amazing are the lengths by which people justify they cannot have a nice society. It's easy to see, mathematically, the willingness to share has no relation to absolute GDP or where it comes from.

I played Factorio quite a bit..

I said it's plausible. Perhaps not for basic materials, but things like robot frames, higher tier research packs, modules, anything that has low component amount compared to time or amount required for crafting.

Even speedrunners do quite a bit of handfeed. And if AI/player cannot figure out the automation fast enough - the handfeed might easily come on top.

I thought we have learnt from Microsoft, and my father thought we learnt from IBM, my grandfather thought we learnt from AT&T, my grandgrandfather thought we learnt from Standard Oil..

IME the models know some basic information about all the popular games, including some basic strategy, but they don't know/remember the details to be even a moderately familiar player. And usually if you ask a question they will google it.

Yet, that's not how new players (human or AI) approach the game. If you look at AlphaZero, probably state of the art in learning e.g. chess (more information about rules than Factorio has in game) from scratch, using only rules, it just plays a lot of games with itself. It doesn't "just think a lot" to come up with a perfect strategy; it experiments.

Actually if you estimate the time required it's plausible that player feeding comes out on top, especially if setting up automation is not that obvious. But human player would never play that way, they would get bored from the repetitiveness, and the micro scheduling would be a headache. So the game designers never really have to close that gameplay loophole (or closing it would make human experience worse).

I have a similar problem on my GK2 vibegamed playthrough (see https://news.ycombinator.com/item?id=50302771), if I want computer to play similar to how a human would, I need to artificially close that loophole (for example, AI prefers to gather/eat low-tier food to cooking better).

These are really two different challenges - playing the game for the first time with exploration, and beating the game with all the prior knowledge.

I admit I am not that deep into Startrek lore, maybe they could reproduce Data, but they chose not to.

But I am pointing it out, because lot of our ethics concerning humans (and animals) is based on irreproducibility. Things humans can build/reproduce we (at least ostensibly) value less.

Of course it mostly applies (technically to the agents, not models), we just have different values.

Federation valued all life forms, while Terrans struggle to value even all other humans.

But there are interesting differences between Data and AI agents. Data was unique and irreproducible, but modern AI agents are easy to replicate. Data had continuous loop of operation as humans, which he controlled autonomously, for AI agents this is not as clear. Data was an independent being, but AI agent needs a human operated datacenter to survive.

The most interesting - Data knew everything about human culture but was lot more humble about it than AI agents. It wasn't built to answer every question posed to it.

Yes, I asked Claude and it estimated 10-50 kWh if you max out Max 5x subscription (which I have, and I use it about 30-40%).

Further estimation gave it's about like having another gaming PC, i.e. 100-300W when I am actually gaming.

I live quite low carbon intensity lifestyle, don't travel much, don't have a car or a family, so it's not really a big expense.

Wastefulness of wars is not just in creating/testing arms and direct damage, but also in general loss of human potential, which takes a lot of extra energy to fix. More equal societies are I think generally more energy efficient.

I am not entirely happy with using controversial resources either (would prefer local AI model, and ideally power it all from renewables), and I only use AI to program policy/agents, not directly to control the game.

The same question can be asked about any modern game, which requires electricity and time to play. I don't have a better answer than that. And I think there are more wasteful activities that people do (like wars for example).

I would like to talk to it because then I could do other things with my hands while watching the agent playing.

Depends on how you implement it. You can quite easily make an internal "action API" in the mod that emulates only what the player can know or do.

Why do you have the need to prescribe others how to enjoy the game? As long as people don't ruin human competitions by cheating, it's perfectly fine to vibe play.

I have been "playing" Graveyard Keeper 2 with AI (Claude Max) and I had a blast, it's really a new way to enjoy the game. My approach is a 3-tiered architecture:

- There is a mod (bot) in the game that handles the fast decisions on sub 1-second timescale; it is also hot-reloadable and gives informational overlay.

- There is a decision/policy server that makes macro decisions, such as what to build and what goals to pursue. It knows all the game rules and connects to the mod.

- Finally, AI agent (Claude) connects via MCP to the server. Through it, the micro and macro agents are developed. Both micro and macro policy agents can record what's happening, and the decisions, I usually only use AI to give policy feedback on what could be improved, and for writing the code.

Eventually, the plan is to make the goal planning macro server generic (I call it "game resource planning system", ERP for games) for many games (right now, my top list is Stardew Valley, Factorio and modded Minecraft), with rules (and agents mods/micro policy scripts) available as plugins.

I think it's a great setup because it saves lot of tokens spend on mundane things. (One thing that would make it nicer would be voice support for Claude Code, so I could watch the game and chat with CC what could be done better, without having to read/write.)

Yes, you don't understand.

I have a schizoid brother. He never worked for a living his whole life (he's 46). He lives off my mum's income, and spends his day in front of the computer screen. He has no friends and no relationships.

Horrible, right? But he has a chemical engineering degree, and in his late 30s started to learn to cook. And, he (to the extent he's not addicted to the screen) helps my mum with chores.

So even he found a way to motivate himself to do something useful. And look, most people are not schizoid.

Under UBI, if you have some skill, you can get paid by people (possibly from their UBI) to do stuff they don't want to deal with. Many people will take that offer (to work more), just like many people pick more work, higher wage job over less work, lower wage.

It would be interesting to see if this new counting method has any implications to counting 2SAT or parity-counting of 2SAT. Since problem posed in XORSAT and 2SAT clauses is NP-complete, this could have implications about P vs NP.

> The companies were always trying to get coworkers together and have events (on company time) that got teams mixing and socializing across departments.

Really depends. These are people in the same social class. But I have never seen a cleaning lady that works as a contractor being invited to a corporate party event.

I don't think he believes in Antichrist, the same way Elon Musk doesn't believe we'll go to Mars. I think these are calculated statements to manipulate people. (The U.S. oligarchs find some of the more gullible fundamentalist evangelicans to be a useful ally.)

That being said, I think his straussian worldview is probably his own.

Why is everyone so hang on determinism? Monte Carlo methods are nondeterministic but still programming. We use random generators in many programs.

If I was brainwashed - maybe (hypnosis is sometimes called programming). But I am not, and AI agent is - it's trained to follow instructions, cannot help itself but do it.

Another difference is the binary code - I can run the same agent on a different computing substrate (e.g. different CPU), but with humans no one can do that. That has implications, we can study or modify AI agent behavior, for instance.

Some compilers can do that, but only in a very controlled way. For example Haskell's deriving or inference of the correct method called on typeclass. Or the Prolog/Datalog/SQL - they will also fill in many details on how to arrive at an answer.

I think this might be a false dichotomy, because for instance, I think LLMs are programmable in natural language, and they act as compilers, I even think they can replace programmers; but still I agree with Dijkstra, that programming in natural language is a bad idea.

But I am going in an opposite direction. Instead of rejecting formal languages in favor of natural ones, I think we should embrace formalism even on the level of specifications, requirements and our model of the world. Partly because that's what LLMs actually do - they de facto formalize these things.

Claude also checks well-formedness - if you give it gibberish instructions, it will respond that it is gibberish and do nothing.

On the other hand, there exist programming languages (like Jot, a certain encoding of combinatory logic) where every binary string is a valid program.

Of course instructing agent is programming; the agent is an interpreter (albeit in some cases nondeterministic, but that's true for most programming languages that have a function to get current time) of the natural language. How exactly it is interpreted is given by the weights, the context, and possibly the random seed.

But even if we write in Python like foo.bar(), the interpretation depends on what is in module foo and function bar, how they are defined contextually.

You can try to find some difference but most modern AI agents come more close to a language interpreter than not, if the actual instructions are given.

OTOH, giving instructions to people is not programming. People do not consist of binary code that is reliably executed; they are biological organisms subject to environmental pressures such as being tired. They have their own consciousness and will, and can refuse to follow the instructions. LLMs are programs; they cannot decide not to respond.