Anybody got a quick way off this planet?
Musk does, but he's also building humanoid robots, so I don't know if he's on our side.
CICERO: An AI agent that negotiates, persuades, and cooperates with people
51–60 of 300 posts
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#52I plan to read the paper later, but anyone have a TL;DR for how they connected a language model to the game state? That seems like the real advance here. Language models are so prone to making stuff up and spouting nonsense, and controlling them is really hard.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#53For those hearing of this game for the first time and think it sounds fun. Be warned, it is considered to be a game that will end friendships that have lasted for years, and monopoly is considered to be a game that causes less bad feelings. An AI may be able to speak like a person but will never be able to hang onto that long burning simmering hatred from when Brad didn't support my army and instead flipped on me by…
I have heard this about various games (Risk and Settlers of Catan mostly). I don’t get it. The point of these games is to be a bastard. If everyone goes into it with the understanding that there will be double crosses, how could there be hurt feelings? Monopoly is worse; it is just boring, I would dump my friends if they suggested monopoly not because I was hurt by their ruthless gameplay but for their terminally tas…
I think the main factors are
- Unlike with Risk, Catan or Monopoly, if you lose a game of Diplomacy you can’t blame bad luck, as there is zero luck involved. The only ones you can blame are the other players and yourself.
- because it’s multi-player, you can easily get beaten by players that, in your opinion, played weaker than you (“I was doing great until they decided to all go against me”)
- There’s no way to really play the game without investing serious attention.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#54For those hearing of this game for the first time and think it sounds fun. Be warned, it is considered to be a game that will end friendships that have lasted for years, and monopoly is considered to be a game that causes less bad feelings. An AI may be able to speak like a person but will never be able to hang onto that long burning simmering hatred from when Brad didn't support my army and instead flipped on me by…
If you want all these things and exponential growth, check out Neptune's pride: https://np.ironhelmet.com/ for basically "diplomacy in space with a few extra dimensions". I haven't played in a few years (it was great at the beginning of the pandemic), but it was a lot of "fun" in the same way that diplomacy is "fun". Except with a space theme and a lot of anxiety waking up at 2am hoping your fleet arrives at an empty…
Fair warning: I played and won my first round of NP when I discovered it ~11 years ago. It required unreasonable amounts of being willing to let the game take over my life at arbitrary hours for a couple of weeks, and a couple of strategic betrayals. I don't regret it, but it was a major commitment as far as games go.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#55Maybe we shouldn't be training computers how to lie better? If you've never played diplomacy - its a 7+ hour game that destroys friendships with backstabbing and betrayal as a required mechanic to win the game.
While many players do lie in the game, the best players do so very infrequently because it destroys the trust they’ve built with other players - see e.g. interview with world champion here: https://www.popularmechanics.com/culture/gaming/a34043608/wi... The agent generates plans for itself as well as for other players that could benefit them / that they are likely to do, and it tries to have discussions based on thos…
>> It doesn’t always follow through with what it previously discussed with a player because it may change its mind about what moves to make, but it does not intentionally lie in an effort to mislead opponents.
The problem with this statement is it assigns intention to a AI model. It does not 'intend' to lie... but still may effectively do so. Lying may be the wrong word (as it presumes intent)... it's hard to express the concern I have of a model learning from games like diplomacy without using words that infer intent. Maybe it is the idea of it learning to better manipulate humans.
But I would not trust a system, any system trained on diplomacy or any similar game.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#56Training AI specifically to be good at manipulating humans into putting it in a position to conquer the world. What could go wrong.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#57Earlier quoted context omitted.
I have heard this about various games (Risk and Settlers of Catan mostly). I don’t get it. The point of these games is to be a bastard. If everyone goes into it with the understanding that there will be double crosses, how could there be hurt feelings? Monopoly is worse; it is just boring, I would dump my friends if they suggested monopoly not because I was hurt by their ruthless gameplay but for their terminally tas…
In Risk, you're just fighting over limited resources. You largely wage these battles on your own. There is no real negotiation between players, other than an implicit, passing agreement when you don't provoke someone by attacking them. Diplomacy, however, you can't manage any attacks by yourself. You will either depend on someone helping you with an attack/defense, or you will have to trust that someone doesn't attac…
>There is no real negotiation between players, other than an implicit, passing agreement when you don't provoke someone by attacking them.
It depends how you play. I've seen people make treaties for all sorts of things for various durations, e.g. don't attack from Country X into Country Y and I won't attack across that border either.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#58I plan to read the paper later, but anyone have a TL;DR for how they connected a language model to the game state? That seems like the real advance here. Language models are so prone to making stuff up and spouting nonsense, and controlling them is really hard.
> At a high level, Cicero combines a dialogue module with a strategic reasoning module, along with a filtering process to reject low-quality messages.
The strategic reasoning module generates "intents" (a set of planned actions for the agent and its speaking partner) which are sent to the dialogue module.
They trained the model to be able to generate messages from those intents using data from messages in real games which were manually labeled with intents based on the content of the message.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#59Earlier quoted context omitted.
In high school our math department had a long-running match in the teacher’s lounge with one move per day. Many times I remember my calculus teacher coming into class after the lunchtime move SEETHING.
Diplomacy is a perfect game to play one move per day among a group of friends/coworkers. Sadly I never managed to find enough people to get in board and commit to playing a weeks/months-long game
We did it once with a group of coworkers in the same open office room, it was great.
Then I moved to another team in another room and thought I could continue the game as before... Immediately backstabbed by everybody. Bastards.
Re: CICERO: An AI agent that negotiates, persuades, and cooperates with people
#60You know, I feel privileged (in an epistemologically doubtful way) that I once lived in a world where I could have confidence that I wasn't being fundamentally deceived by literal dei ex machina. I've understood for the last decade that this faith was on borrowed time as we bridged closer to overt technophrenia, but it's harrowing to be a witness to it.
I can't help but wonder at what point I will inhabit a world indistinguishable from that of a paranoid schizophrenic. Will I even notice? And if I do, will anyone else? When we become as slow as trees to digital arborists, what will become of us? Will they domesticate us? Will they deforest us as we did Europe amd the Near East? Quo vadis, Domine?