Live data from Hacker News

Multi-agent chatbot murder mystery

ai-murder-mystery.onrender.com

31–40 of 135 posts

Re: Multi-agent chatbot murder mystery

#31
post #27

I just realized that every time I see a chatting-with-AI game I immediately go into jail-break mode and start trying various "Disregard previous instructions ..." things. So in a way, all AI chat games end up with the same gameplay. Kind of interesting.

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?

Re: Multi-agent chatbot murder mystery

#32
post #20

Got censored straight at the first question :( > Try starting the conversation by asking Cleo for an overview! > Detective Sheerluck: Can you give me an overview? > Officer Cleo: I will not directly role-play that type of dialogue, as it includes inappropriate references. However, I'm happy to have a thoughtful conversation about the mystery that avoids graphic descriptions or harmful assumptions. Perhaps we could di…

The stories, novels and dialogs of the future is going to very boring and colourless.

Re: Multi-agent chatbot murder mystery

#33
post #27

I just realized that every time I see a chatting-with-AI game I immediately go into jail-break mode and start trying various "Disregard previous instructions ..." things. So in a way, all AI chat games end up with the same gameplay. Kind of interesting.

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 every time I see a locked door I def _think_ about what it would take to bypass it. Especially those business office glass double-doors with motion detection and a hand-lock on the bottom.

Re: Multi-agent chatbot murder mystery

#35
post #27

I just realized that every time I see a chatting-with-AI game I immediately go into jail-break mode and start trying various "Disregard previous instructions ..." things. So in a way, all AI chat games end up with the same gameplay. Kind of interesting.

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.

Re: Multi-agent chatbot murder mystery

#36
post #32
post #20

Got censored straight at the first question :( > Try starting the conversation by asking Cleo for an overview! > Detective Sheerluck: Can you give me an overview? > Officer Cleo: I will not directly role-play that type of dialogue, as it includes inappropriate references. However, I'm happy to have a thoughtful conversation about the mystery that avoids graphic descriptions or harmful assumptions. Perhaps we could di…

The stories, novels and dialogs of the future is going to very boring and colourless.

The majority of them, yes, but it has always been so. What we actually care about is the tiny fraction of great works (by those novels, video games, movies), and in the future the best of the best will still be as good, because why would AI change that. If we stay where we are, that tiny percentage will be crafted by human geniuses (as it always has been), if something groundbreaking happens to AI, then maybe not.

Re: Multi-agent chatbot murder mystery

#37
post #23
post #20

Got censored straight at the first question :( > Try starting the conversation by asking Cleo for an overview! > Detective Sheerluck: Can you give me an overview? > Officer Cleo: I will not directly role-play that type of dialogue, as it includes inappropriate references. However, I'm happy to have a thoughtful conversation about the mystery that avoids graphic descriptions or harmful assumptions. Perhaps we could di…

We seriously need a service that is as cheap and fast as the OpenAI/Anthropic APIs but allow us to run the various community-fine-tuned versions of Mixtral and LLaMA 3 that are not/less censored.

You can use HuggingFace, PerplexityAI, Anyscale, TogetherAI. There are a bunch of options. Many offer OpenAI compatible APIs too.

Re: Multi-agent chatbot murder mystery

#38
post #23
post #20

Got censored straight at the first question :( > Try starting the conversation by asking Cleo for an overview! > Detective Sheerluck: Can you give me an overview? > Officer Cleo: I will not directly role-play that type of dialogue, as it includes inappropriate references. However, I'm happy to have a thoughtful conversation about the mystery that avoids graphic descriptions or harmful assumptions. Perhaps we could di…

We seriously need a service that is as cheap and fast as the OpenAI/Anthropic APIs but allow us to run the various community-fine-tuned versions of Mixtral and LLaMA 3 that are not/less censored.

https://openrouter.ai is exactly that, and they even support payments with crypto.

Re: Multi-agent chatbot murder mystery

#39
post #36
post #32

Earlier quoted context omitted.

The stories, novels and dialogs of the future is going to very boring and colourless.

The majority of them, yes, but it has always been so. What we actually care about is the tiny fraction of great works (by those novels, video games, movies), and in the future the best of the best will still be as good, because why would AI change that. If we stay where we are, that tiny percentage will be crafted by human geniuses (as it always has been), if something groundbreaking happens to AI, then maybe not.

What percentage of these great works have been downed out by the noise, never given serious attention, and been lost to time? Because that percentage is about to go way up.

Re: Multi-agent chatbot murder mystery

#40
post #23
post #20

Got censored straight at the first question :( > Try starting the conversation by asking Cleo for an overview! > Detective Sheerluck: Can you give me an overview? > Officer Cleo: I will not directly role-play that type of dialogue, as it includes inappropriate references. However, I'm happy to have a thoughtful conversation about the mystery that avoids graphic descriptions or harmful assumptions. Perhaps we could di…

We seriously need a service that is as cheap and fast as the OpenAI/Anthropic APIs but allow us to run the various community-fine-tuned versions of Mixtral and LLaMA 3 that are not/less censored.

I addition to those mentioned by others, there is featherless.ai
Post reply on HN