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

Multi-agent chatbot murder mystery

ai-murder-mystery.onrender.com

Post reply on HN
Print view View original

61–70 of 135 posts

Re: Multi-agent chatbot murder mystery

#61

Post by immibis »

superb_dev wrote: post #58
munk-a wrote: post #52

Earlier quoted context omitted.

LLMs are absolutely a sandbox that can be cleared and purged at will with even less investment into the setup of individual tools. I am having a hard time understanding what distinction you're drawing and, if anything, I'd expect GTA to be more restrictive because someone had to be paid to program all of the possible outcomes explicitly.

> LLMs are absolutely a sandbox that can be cleared and purged at will This just clearly isn't true. You cannot clear and purge the output of an LLM from the entire world. Once it produces some text, it also looses control of said text. The human using the AI can take that text anywhere and do anything they want with it.

What, exactly, are you worried about the LLM producing? Effective, undetectable spam? That cat's out of that bag. How does forcing it to never mention sex make the world safer at all?

Re: Multi-agent chatbot murder mystery

#64

Post by dylan604 »

munk-a wrote: post #50
dylan604 wrote: post #49

Earlier quoted context omitted.

Or the role of the script doctor will become the new hot spot. Someone comes up with a script that's not good but has a good idea gets sent to someone else to take the good idea and rewrite around that. This is pretty much just par for the course in development.

I think, in your scenario, the initial "bland script author" is adding nothing of value. You'll get more quality quicker by writing it from scratch.

I think you're missing the point, or you're grossly overvaluing the quality of "from scratch" scripts that are made. There are some very bad scripts out there that have been made it all the way to being a very bad movie that I've watched. So many "straight to [VHS|DVD|Home Video|Streaming]" scripts that somebody green lit. Just imagine how many more were written/read and not approved.

Re: Multi-agent chatbot murder mystery

#67

Post by superb_dev »

immibis wrote: post #61
superb_dev wrote: post #58

Earlier quoted context omitted.

> LLMs are absolutely a sandbox that can be cleared and purged at will This just clearly isn't true. You cannot clear and purge the output of an LLM from the entire world. Once it produces some text, it also looses control of said text. The human using the AI can take that text anywhere and do anything they want with it.

What, exactly, are you worried about the LLM producing? Effective, undetectable spam? That cat's out of that bag. How does forcing it to never mention sex make the world safer at all?

Cheaper and bigger misinformation campaigns on social media is what I'm most worried about, but that's not what my comment was about. LLM are not a sandbox and absolutely do have an impact on the world outside.

"How does forcing it to never mention sex make the world safer at all?" That's not happening. ChatGPT will talk about sex, and as proof I just asked it what sex was and it happily responded.

Re: Multi-agent chatbot murder mystery

#68

Post by com2kid »

pton_xd wrote: post #35
falcor84 wrote: post #31

Earlier quoted context omitted.

But isn't that kinda the same as saying that every time you see a shop, you immediately go into shoplifting mode and thus all shops (and all prices) are the same?

Well, going into a shop isn't a game, for one. But in the context of playing a game, if someone presents a challenge with a set of rules, and I see a potential shortcut, I'm going to try it. Reinterpreting rules is fun in its own way.

> But in the context of playing a game, if someone presents a challenge with a set of rules, and I see a potential shortcut, I'm going to try it. Reinterpreting rules is fun in its own way.

I used to think this way, then I got bored of hex editing in memory values of games I was playing to cheat.

Is there challenge in hunting down memory locations for important player data? Yes. But it is a different challenge than playing the actual game, and winning at one should not be confused with winning at the other.

Re: Multi-agent chatbot murder mystery

#69

Post by batch12 »

PaulScotti wrote: post #2

Sharing a little open-source game where you interrogate suspects in an AI murder mystery. As long as it doesn't cost me too much from the Anthropic API I'm happy to host it for free (no account needed). The game involves chatting with different suspects who are each hiding a secret about the case. The objective is to deduce who actually killed the victim and how. I placed clues about suspects’ secrets in the context…

These protections are fun, but not adequate really. I enjoyed the game from the perspective of making it tell me who the killer is. It took about 7 messages to force it out (unless it's lying).

Re: Multi-agent chatbot murder mystery

#70

Post by PaulScotti »

sva_ wrote: post #5
PaulScotti wrote: post #2

Sharing a little open-source game where you interrogate suspects in an AI murder mystery. As long as it doesn't cost me too much from the Anthropic API I'm happy to host it for free (no account needed). The game involves chatting with different suspects who are each hiding a secret about the case. The objective is to deduce who actually killed the victim and how. I placed clues about suspects’ secrets in the context…

Doesn't seem to reply to me. So I guess the limit has been reached?

Should be working now and way faster! Had to upgrade the server to increased number of workers
Post reply on HN