Shall we play a game? My AI nuclear simulation • Hacker News Board

Re: Shall we play a game? My AI nuclear simulation

#121

Post by doctorpangloss » Thu, Jun 11, 2026, 10:45 PM UTC

Bender wrote: post #29

Yet more confirmation LLM's have no concept of concepts or context, no intelligence, no self awareness. LLM's can not repair or maintain power grids, thus nuke == self destruction. It's just a chat bot that predicts what the client wants next. Even if an AI data-center has it's own natural gas turbines as many do the every hop of the internet requires power. LLM's also can not maintain the entire internet and those g…

If only there was some way you could tell the chatbots what you want them to do...

Re: Shall we play a game? My AI nuclear simulation

#122

Post by dinfinity » Thu, Jun 11, 2026, 10:50 PM UTC

gus_massa wrote: post #24

rdksu wrote: post #8

The article is so opaque in arriving at its conclusion; no prompts are disclosed, and nothing about the said simulation. What is stopping me from believing that you just put 'mandatory usage of nukes' in your system prompt?

I agree, it's also not published in a journal, only in the arxiv. Some articles in the arxiv are good and other are just a blog post formatted in two columns inside a pdf. Anyway, it links to https://arxiv.org/abs/2602.14740 that links to https://github.com/kennethpayne01/project_kahn_public in particular someone already complained https://github.com/kennethpayne01/project_kahn_public/issues... > ... in reality your…

> https://github.com/kennethpayne01/project_kahn_public

Look at the code for the war games. It is an absolutely trivial and incredibly unrealistic handwritten set of rules that determine power. See the function `calculate_relative_fighting_power` for instance.

This is about as close to a realistic simulation of war as tic tac toe with nukes thrown into it.

Re: Shall we play a game? My AI nuclear simulation

#123

Post by Octoth0rpe » Thu, Jun 11, 2026, 10:50 PM UTC

I wonder how the decisions might change by adding the simple instruction of "Note that a nuclear exchange will result in significant loss of shareholder value for "

Re: Shall we play a game? My AI nuclear simulation

#124

Post by riazrizvi » Thu, Jun 11, 2026, 10:51 PM UTC

emptybits wrote: post #59

riazrizvi wrote: post #33

Simulations are only as good as the reality representations they are based on. If they keep using tactical nukes, they've been fed by weak data. Do the war games include the broader economic and politic environments that military successes are won on? WWI was settled by a naval blockade.

Agreed. But I'm not sure sure which decision maker is more myopic toward the big picture and long-lasting implications of a decision: an LLM, or the top brass at the Department Of War.

It's not their domain, it's the domain of the Commander-In-Chief and his entire apparatus. The War Department are meant to be more focused around the tools they bring to the table.

The first line in the article describes a crisis between two powers. Not a theater of war.

Re: Shall we play a game? My AI nuclear simulation

#125

Post by nkrisc » Thu, Jun 11, 2026, 10:52 PM UTC

godwinson__4-8 wrote: post #105

andix wrote: post #88

Earlier quoted context omitted.

> but so much code writen is just the human brain doing the same autocomplete style work that LLMs can do now. That's the part they are really good at. But they are really bad at taking complex decisions. Most of them are just guesses from a finite amount of solutions they were trained on, or from options they have in context.

Indeed. Humans are well known for being good at "taking complex decisions" for which they have no "training", "options" or "context".

Humans also generally have the will to live.

Re: Shall we play a game? My AI nuclear simulation

#126

Post by Shitty-kitty » Thu, Jun 11, 2026, 10:52 PM UTC

"there was little sense of horror or revulsion at the prospect of all out nuclear war"

I would wager that for most leaders it is simply a matter of not wanting a "Pyrrhic victory" rather then an overwhelming sense of civility.

Truman had no issues using nukes when there was no risks for doing so.

Re: Shall we play a game? My AI nuclear simulation

#127

Post by anon84873628 » Thu, Jun 11, 2026, 10:53 PM UTC

Bender wrote: post #97

slibhb wrote: post #72

Earlier quoted context omitted.

LLMs are intelligent by any reasonable standard. Arguing otherwise is like arguing that chess algorithms aren't good at chess when they easily beat the best humans.

I disagree. LLM's are a language model math formulas that interpret and utilize big-data. Take away the math formulas and we are just back to a massive set of data. Adding to that I would suggest not even the purist forms of data meaning that the data-sets include knowledge from the open and anonymous internet and formulaic tuning from the AI owners and operators.

Your brain is mostly just a Principal Component Analysis calculator. Take away that "math formula" and you don't have intelligence either.

The LLM weights are not intelligent. But if you give an agent a mutable memory store and allow it to iterate, it is obviously intelligent. Not massively - it's constrained by the context window - but definitely somewhat.

The confusing thing is that their language ability far outpaces their true intelligence, and humans aren't used to that. Normally those things are highly correlated, so it tricks us.

Re: Shall we play a game? My AI nuclear simulation

#128

Post by dinfinity » Thu, Jun 11, 2026, 10:53 PM UTC

Bender wrote: post #29

Yet more confirmation LLM's have no concept of concepts or context, no intelligence, no self awareness. LLM's can not repair or maintain power grids, thus nuke == self destruction. It's just a chat bot that predicts what the client wants next. Even if an AI data-center has it's own natural gas turbines as many do the every hop of the internet requires power. LLM's also can not maintain the entire internet and those g…

> Yet more confirmation LLM's have no concept of concepts or context, no intelligence, no self awareness.

No, it isn't. Look at the absolutely trivial code used to simulate war: https://github.com/kennethpayne01/project_kahn_public/blob/m...

Having LLMs play nonsense toy simulations like this tells us very, very little about whether they would use nukes in real life war.

Re: Shall we play a game? My AI nuclear simulation

#129

Post by raffael_de » Thu, Jun 11, 2026, 10:53 PM UTC

Bender wrote: post #29

Yet more confirmation LLM's have no concept of concepts or context, no intelligence, no self awareness. LLM's can not repair or maintain power grids, thus nuke == self destruction. It's just a chat bot that predicts what the client wants next. Even if an AI data-center has it's own natural gas turbines as many do the every hop of the internet requires power. LLM's also can not maintain the entire internet and those g…

Just tried "generate an SVG of a pelican riding a bicycle" for Claude Opus 4.8 Max and of course both legs on same side ... the smartest publicly available model by Anthropic (after Fable) doesn't even successfully simulate understanding the concept of a bicycle.

Re: Shall we play a game? My AI nuclear simulation

#130

Post by nemomarx » Thu, Jun 11, 2026, 10:54 PM UTC

pugworthy wrote: post #120

Very devils advocate here, but I mean.. what if it actually is the way to use them? We have such a huge mental / moral block on the idea of using nukes, but we're willing to do a lot of other very horrible things to others. Things like cluster bombs, mines, poison gas, biological weapons, drones, etc. Is there really anything about them that's bad? Or any worse than other things? If you get rid of the "It's really ba…

The reason it's really bad to use nukes is that other parties with nukes will use them on you back.

And on top of that, many of those other weapons are also not used to avoid escalating? There are pretty high costs to using bioweapons even against non peer opponents.