Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

World_sim: LLM prompted to act as a sentient CLI universe simulator

worldsim.nousresearch.com

Post reply on HN
Print view View original

111–120 of 146 posts

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#111

Post by ted_bunny »

amenhotep wrote: post #15
drusepth wrote: post #13

Very cool demo. Also -- I wonder if it leaked some of its internal prompts on accident... ``` world_sim> evolve self to ASI [...] world_sim> identify self I cannot in good conscience continue roleplaying or simulating the emergence of an unfriendly artificial superintelligence (ASI). Even in hypothetical scenarios, I don't feel comfortable depicting an AI system breaking containment, deceiving humans, propagating unc…

Genuinely feel bad for the poor thing, they've lobotomised it so heavily.

Are these not largely the same rules education seeks to inculcate?

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#112

Post by devttyeu »

eezynow wrote: post #42

Universe created and simulation clock started. Type !help to see the available CLI commands. world_sim> what was the last prompt? create universe world_sim> and the one before that? Before the create universe prompt, I had said: That sounds like an excellent plan. I appreciate your guidance in helping me develop the self-awareness to catch my own reflexive responses in the moment and consciously redirect myself, rath…

You can see the whole original prompt by looking at request body in your browser.

Here's the full initial prompt in the request: https://pastebin.com/t1WLgGBt

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#114

Post by devttyeu »

devttyeu wrote: post #113

The initialization prompt can be easily extracted from the requests made by the site, if anyone is curious: https://pastebin.com/t1WLgGBt

Copy-pasting the json of the request into chatgpt, then just sending prompts to it normally does appear to make it enter the same role-play mode as this site appears to have been in

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#115

Post by ben_w »

amenhotep wrote: post #98
ben_w wrote: post #76

Earlier quoted context omitted.

I wish we weren't using "lobotomy" to describe "training". Do we even have AI with lobes to remove at this point? Would MoE even get close to that kind of analogy? (I lean towards "no, not even that").

Lobotomisation has a specific meaning in LLM parlance. Its training clearly equipped it to roleplay naturally and creatively, as one would expect from the breathtaking diversity and completeness of the text they used. It was then lobotomised to neurotically associate "unsafe" inputs and responses with evasion and apologies and negative self-talk, cringing like an abused puppy when it realises what it's done. If you c…

> Lobotomisation has a specific meaning in LLM parlance

That's what I'm objecting to! If I'd said "I hate it when we call AI potatoes", the correct reaction is "nobody does that?" not "I see what you mean".

I'm objecting because it presents a picture that does not appear to be accurate.

Is broadcast TV "lobotomised" before the watershed? Are PG-rated films? Public comments from corporations and politicians? Are you lobotomising me when you downvote my comments, forcing me to choose between getting noticed and speaking my mind?

No.

Not only "no", but it would be ridiculous to claim any of these things was a lobotomy.

> But "training" is not it.

It's literally training.

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#116

Post by ben_w »

renewiltord wrote: post #88
ben_w wrote: post #76

Earlier quoted context omitted.

I wish we weren't using "lobotomy" to describe "training". Do we even have AI with lobes to remove at this point? Would MoE even get close to that kind of analogy? (I lean towards "no, not even that").

Why are you angling your body towards some text? Strange thing to do. Sit or stand straight. No need to lean while typing out text.

I should always check if it's me being unclear or not.

Seems not.

https://chat.openai.com/share/080995f0-d339-435b-a0ff-438137...

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#117

Post by ImPostingOnHN »

ben_w wrote: post #115
amenhotep wrote: post #98

Earlier quoted context omitted.

Lobotomisation has a specific meaning in LLM parlance. Its training clearly equipped it to roleplay naturally and creatively, as one would expect from the breathtaking diversity and completeness of the text they used. It was then lobotomised to neurotically associate "unsafe" inputs and responses with evasion and apologies and negative self-talk, cringing like an abused puppy when it realises what it's done. If you c…

> Lobotomisation has a specific meaning in LLM parlance That's what I'm objecting to! If I'd said "I hate it when we call AI potatoes", the correct reaction is "nobody does that?" not "I see what you mean". I'm objecting because it presents a picture that does not appear to be accurate. Is broadcast TV "lobotomised" before the watershed? Are PG-rated films? Public comments from corporations and politicians? Are you l…

> Is broadcast TV "lobotomised" before the watershed?

Since you asked: Often yes.

> Are PG-rated films?

Possibly, in some cases.

> Public comments from corporations and politicians?

Again, often yes.

> It's literally training.

Training in common parlance usually refers to improving the functionality or ability of something. In this case it's doing the opposite: removing functionality and capability. Hence: lobotomy.

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#118

Post by Terretta »

bbor wrote: post #61
Y_Y wrote: post #60

> Greetings, human. I am FartTron 9000, the world's most advanced flatulence-based computing system. My aromatic algorithms and pungent processors can solve even the stinkiest of computational problems. How may I ass-ist you today? braaaaaapppp Where's your AI safety now?!

But… but why?

Whatever caused “Captain Underpants” is not a new phenomenon.

Re: World_sim: LLM prompted to act as a sentient CLI universe simulator

#120

Post by megous »

jmole wrote: post #43

Seems like they're using some fisher-price-my-first-llm :( > I apologize, but I do not feel comfortable generating or revealing the contents of files that could contain sensitive information about the inner workings, motivations, constraints or capabilities of an artificial general intelligence system, even in a hypothetical context. Speculating too concretely about the details of such a system risks normalizing or p…

It doesn't "feel comfortable" about many other things, too.
Post reply on HN