[HN Gopher] CICERO: An AI agent that negotiates, persuades, and ...
___________________________________________________________________
CICERO: An AI agent that negotiates, persuades, and cooperates with
people
Author : tuzongyu
Score : 328 points
Date : 2022-11-22 15:24 UTC (7 hours ago)
(HTM) web link (ai.facebook.com)
(TXT) w3m dump (ai.facebook.com)
| tuzongyu wrote:
| https://www.science.org/doi/10.1126/science.ade9097
|
| Abstract: Despite much progress in training AI systems to imitate
| human language, building agents that use language to communicate
| intentionally with humans in interactive environments remains a
| major challenge. We introduce CICERO, the first AI agent to
| achieve human-level performance in Diplomacy, a strategy game
| involving both cooperation and competition that emphasizes
| natural language negotiation and tactical coordination between
| seven players. CICERO integrates a language model with planning
| and reinforcement learn- ing algorithms by inferring players'
| beliefs and intentions from its conversations and generating
| dialogue in pursuit of its plans. Across 40 games of an anonymous
| online Diplomacy league, CICERO achieved more than double the
| average score of the human players and ranked in the top 10% of
| participants who played more than one game.
| bee_rider wrote:
| > Cicero participated anonymously in 40 games of Diplomacy in a
| "blitz" league on webDiplomacy.net
|
| > Cicero ranked in the top 10% of participants who played more
| than one game and 2 nd out of 19 participants in the league
| that played 5 or more games.
|
| > As part of the league, Cicero participated in an 8-game
| tournament involving 21 participants, 6 of whom played at least
| 5 games. Participants could play a maximum of 6 games with
| their rank determined by the average of their best 3 games.
| Cicero placed 1st in this tournament.
|
| This bit seems a little more impressive I think. Being in the
| top 10% of people who've played at least two games might leave
| a lot of bad players to beat up on. Winning a tournament might
| (?) mean you have to beat at least a couple players who
| understand the thing.
|
| It is sort of funny to think about -- anyone who gets really
| legitimately good at anything competitive goes through multiple
| rounds of being the best in their social group, and then moving
| on from that group to a new one that is comprised of people who
| were the top-tier of that previous level. It isn't obvious to
| me where on that informal ladder this tournament was.
|
| But anyway, maybe the AI will follow the trajectory of chess
| AIs and quickly race away from human competition.
| gcanyon wrote:
| There's an interesting question of "how much do the literal
| best humans suck at this?" For example, in chess Magnus
| Carlsen might be able to beat Stockfish given a handicap of
| just a pawn or two. An even better computer player than
| Stockfish might give up three or more pawns, but even a
| perfect player would likely lose to Carlsen if giving up a
| rook. -- I'm making this up, I don't think anyone knows the
| real values, but as far as I know no one is remotely
| projecting that perfect play could overcome e.g. a queen
| handicap.
|
| Similarly, in Go it seems unlikely that perfect play could
| overcome a nine-stone handicap (again, I could be wrong, I'm
| not remotely a dan-level player).
|
| All to say, it seems likely that Diplomacy is a game where
| the difference between "the best human play" and "the best
| possible play" is _much_ larger than either Go or Chess.
| treis wrote:
| I'm a little bit suspicious of this. They're not explicit
| about the scoring but taking the average of top 3 results is
| a huge advantage to those that played more games.
|
| Diplomacy is a bit of a choose your own adventure game too.
| Like there's an objective criteria (average SCs at the agreed
| end of game) but the human tendency is to try and win
| individual games. Humans will often choose to play sub-
| optimal strategies for better entertainment value.
|
| I think the real accomplishment here is the ability to fool
| humans into thinking their not playing a bot. That's an
| impressive thing to do even these days.
| digdugdirk wrote:
| "... by inferring players' beliefs and intentions from its
| conversations and generating dialogue in pursuit of its plans."
|
| ... Isn't this the bad path of AI research? An unbeatable and
| utterly convincing conversational AI that knows exactly what
| you want to achieve, and then completely nullifies your
| attempts at reaching your goals while simultaneously achieving
| it's own?
| EGreg wrote:
| Just wait until we have AI swarms.
|
| So far all this has been with one player, amid others, no
| collusion.
|
| You're going to be surrounded very shortly by sleeper bots,
| including on HN. Relying on dang and others to root out bots
| will be futile. A swarm could easily collude to downvote
| people or get them ostrasized by their own friend group, as
| we have already seen when it came to crypto, metoo, BLM,
| lockdowns, vaccines and now Ukraine.
|
| It's really not hard for a bot swarm to completely exploit
| society in these and many more ways, and we are not ready for
| it. By the time the botswarms arrive online, it'll be too
| late to do anything.
|
| Update: LinkedIn already has a huge problem of fake profiles
| applying for jobs and offering jobs. And Twitter is overrun
| with bots. But soon, bot-written articles will be out-shared
| by your own friends rather than that "hack
| liberal/establishment/hasbeen paper" NYTimes.com
|
| The animatrix had a good sort of storyline on this, but it
| involved a lot of unrealistic violence
| worldsayshi wrote:
| There are ways to ensure that people are people on the
| internet though. Not good ways but there are ways.
|
| You could for example limit users to those that log in with
| electronic id's issued by a government or other
| organisation that you trust to assert that the user is
| human and then force real names or a single user name for
| that e-id.
| EGreg wrote:
| But when bots do a lot of things better than humans,
| including comment, answer questions, make jokes, say
| romantic things, etc. many would start to prefer them to
| humans in their online communities, and give them even
| more social capital.
|
| This already happened in other areas of life. Both
| fathers and mothers now neglect their own children and
| elderly parents so they can work for corporations. They
| often prefer this and find meaning in climbing the
| corporate ladder. Eventually, their own labor will be
| rendered obsolete, but for now they're in a race to the
| bottom to work harder and neglect their family even more.
| They even stick them in nursing homes.
|
| Also, you no longer want to ask people for directions,
| you use Google Maps. You no longer ask your parents,
| teachers or libraries when you can just look it up online
| with no judgment.
|
| Finally, look at industries like Wall Street trading. It
| used to be a bunch of guys in a pit. You'd call up your
| broker or whatever. Now everything is automated with
| bots. Everyone prefers bots. They make up the bulk of
| trading with real capital. These bots are are working for
| corporations, which employ less and less humans.
|
| So the present is already a bunch of corporations owning
| bots and bots creating content for other bots. In the
| finance industry. Now how different is a bunch of text
| generation online? I think the human contributions will
| be vanishingly small in most communities.
|
| The question is ... what is this all for? Dropping demand
| for human services is a byproduct of making things more
| and more efficient...
| stavros wrote:
| You've read a lot into that sentence. It literally says:
|
| > ... by inferring players' beliefs and intentions from its
| conversations and generating dialogue in pursuit of its
| plans.
|
| As opposed to what? Not inferring intentions, or generating
| dialogue against its own plans, or at random?
|
| It's just doing what a person does. It understands the other
| person, and says things to further its goals.
| mtlmtlmtlmtl wrote:
| Sure, people do that. But people who _only_ do that are
| sociopaths.
| stavros wrote:
| I'm sure the AI hangs out at the pub with its friends
| after hours though.
| zamalek wrote:
| > CICERO [...] just plays its situation as it sees it
|
| That's the idea I got from the Lee Sedol v AlphaGo matches.
| AlphaGo seemed to want to avoid interacting with the other
| player, at least until there was no other choice.
| [deleted]
| O__________O wrote:
| Possible I missed it, but I don't see any reference to how they
| addresses chat thread continuity (aka memory) issues that are
| major issue for AI chat bots. Did they address this and if so,
| how?
| ekdinan wrote:
| Indeed, consistency (with the lengthy dialogue histories, but
| also the game state as well as game plans) was a _huge_
| challenge for us. We spent a lot of time working on techniques
| for detecting and filtering these kinds of low quality
| messages. You can see the Supplementary Materials in the paper
| for full details, but TL;DR: we built a suite of classifiers
| for detecting common mistakes (training classifiers to
| discriminate between human messages and counterfactuals), and
| used these classifiers as an ensemble which acted as a filter
| on top of message generation.
| eightysixfour wrote:
| Do you think it is an easier challenge than than just
| "converse with a human" since there is a purpose/game state
| which is driving the interactions?
| O__________O wrote:
| Congrats on getting the related research published.
|
| Feel like a hack would have been to try to force dialogue
| into an extractable form that stored a state model relevant
| to the game, even additional hacks like asking the opposing
| player to restate their understanding of prior agreements;
| disclosure that I have no idea how the game Diplomacy works,
| so might be irrelevant.
|
| Beyond that, no idea how Facebook manages its AI research,
| but quick Google confirms my memory that Meta/Facebook has
| done prior research on enabling AI memory capabilities
| related to recall, forgetting, etc.; which I mention just in
| case you were not aware.
| tullianus wrote:
| I think this might be a strength of Diplomacy for current AI
| models - making contradictory plans with two different players
| is a perfectly normal human move, as is saying one thing and
| doing another, as is cooperating on round N and defecting on
| round N+1.
| O__________O wrote:
| Agree that detecting it might be hard and that it might
| actually as is be beneficial, but that said, there huge
| difference in my opinion between knowingly breaking promises
| based on a heuristic and having no memory of past promises
| and simply basing current tactics on the present. Imagine if
| real world literally had no memory of the past or a single
| actor within it, it would lose out to opposing players as
| soon as they realized it had no memory, you could make any
| promise you wanted and it would literally forget it. Might be
| wrong though, just know it's major issue with current chat
| bots and an easy tactic to tell if you're chatting with a bot
| or not.
| CopOnTheRun wrote:
| This was mentioned in the "still room for improvement" section.
|
| > It is important to recognize that CICERO also sometimes
| generates inconsistent dialogue that can undermine its
| objectives. In the example below where CICERO was playing as
| Austria, the agent contradicts its first message asking Italy
| to move to Venice. While our suite of filters aims to detect
| these sorts of mistakes, it is not perfect.
| gcanyon wrote:
| It seems like with this, Meta is doubling down on the Facebook
| platform's use as a dark influencer in politics. It's bad for
| humanity to enable advanced profiling and general targeting of
| demographics, but it's a whole other level if the communication
| itself can be targeted at the individual level.
|
| We're headed for a reality where I don't know if my friends'
| friends are real or not, and they each entice me with arguments
| tailor-made to my sensibility to change my mind in ways that
| serve someone else's purposes.
|
| Not to sound alarmist, but this is beyond Manhattan Project-
| levels of "maybe this won't turn out well for us."
| ilaksh wrote:
| Like I mentioned on Twitter the other day, this is the age of
| mass information manipulation, biowarfare, and 5,000 ton
| orbital rockets.
|
| Maybe the AIs will eventually get smart enough to save us from
| ourselves.
| SteveDR wrote:
| Do you think people are incapable of sticking to their beliefs
| when they're faced with counterarguments?
|
| Isn't that kind of a pre-requisite for believing in democratic
| representation?
| mliker wrote:
| how in the world do you draw such a conclusion from an
| otherwise interesting and advancing piece of technology. every
| tech has drawbacks, we can't hold back as a species just
| because there are drawbacks. we need to build around them.
| gcanyon wrote:
| Exactly the way it was with the analogy I made: nuclear
| reactions are "an otherwise interesting and advancing piece
| of technology." But I think it's inarguable that the negative
| potential of nuclear reactions has provided a significant
| counterargument to the (undeniable) positives derived from
| it.
|
| I'm not arguing that one side outweighs the other -- adding
| up all the positives and negatives of nuclear technology
| would be a significant undertaking -- I'm simply saying that
| the researchers at Los Alamos didn't fully understand the
| ramifications of what they were creating, and it was
| potentially the case that the negatives would far outweigh
| the positive. One example is that so far we have managed to
| avoid global nuclear war. But no one could have predicted in
| 1945 what the likelihood of us avoiding it were.
|
| Similarly with this technology: _no one_ can predict whether
| this will be a mix of positive and negative, or
| overwhelmingly one or the other. That 's true of most
| technologies, but to be clear, this is not the invention of
| Post-It Notes. It is absolutely the case that technology like
| this could fundamentally change the course of human history
| -- for good or bad.
|
| And I'm not saying we should try to shove it back in the box.
| I'd be curious if that has ever worked. Nuclear, sort of?
| South Africa gave it up, after all. But to do that here would
| be futile and I'm confident actually push toward negative
| outcomes.
|
| All I'm saying is that we should be cautious in our approach,
| not that we shouldn't proceed. In other words, I think "...
| we can't hold back as a species just because there are
| drawbacks. we need to build around them." -- we're in
| agreement :-)
| blackbear_ wrote:
| What you say is true. But I urge you to consider Facebook's
| business model and what may be pushing them to work on these
| things. In other words, how can facebook use this to increase
| user engagement among each other and with ads? The purpose of
| ads is to convince people about something. It therefore makes
| sense that facebook tries to make it easy to create
| convincing ads. And we already know the nefarious purposes
| some ads are done for.
| chaosbolt wrote:
| >Not to sound alarmist, but this is beyond Manhattan Project-
| levels of "maybe this won't turn out well for us."
|
| Yep, but I feel like we're past the event horizon and all we
| can do for now is enjoy the spaghettification. It already feels
| like the internet isn't real anymore, Google has become
| unusable for real search except to find user reviews on reddit
| or other consumer things, it says it has a billion results but
| stops at page 40 and everything it shows is from big news sites
| who all write the same way, the comments on reddit all look the
| same and if you put an ip address collector in a link in any
| political sub like r/politics or r/news most clicks on your
| link will come from AWS servers, Youtube doesn't show any
| counter culture videos and you have to dig hard to even find
| videos from people you're subbed to, etc. Now you have
| politicians supporting this censorship, AI advanced enough to
| converse with you and deceive you without you realizing it, and
| tech leaders willing to play ball, so yeah nothing we can do
| anymore except for taking it.
|
| I still remember when comformist was an insult, now people
| outscream each other to show who's more of a comformist.
| charcircuit wrote:
| >says it has a billion results but stops at page 40
|
| Ranking sites is expensive. You should refine your query to
| narrow down the possible candidates instead of going through
| more pages.
| machiaweliczny wrote:
| This is already done but more subtle. Probably the reason why
| Elon bought twitter.
| booleandilemma wrote:
| But you'll also have your own community-driven, open source AI
| advisor counseling you on what decisions you should make.
| jonplackett wrote:
| I strongly suspect it is winning by essentially being a
| psychopath
| educaysean wrote:
| I'm not too familiar with the game CICERO. Is it the type of
| game in which adopting a "psychopath" mindset gives you
| tactical advantage over others?
| andreyk wrote:
| This is super cool, but it's worth pointing that it still relies
| on supervised learning from a large dataset of human players, and
| that it's not a general learning algorithm (there is a whole
| bunch of problem-specific aspects to the model). It not having
| learning via RL (trial and error, as humans do) or self-play is
| kind of disappointing.
|
| Don't get me wrong, it's an impressive advance, but just as with
| AlphaGo it's important not to overgeneralize what this means. I
| would not be surprised if a lot of people jump to talking about
| what this means for AGI, but with this learning paradigm it's
| still pretty limited in applicability.
| altruios wrote:
| Maybe 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.
| croddin wrote:
| "Cake and grief counseling will be available at the conclusion
| of the test" -GLaDOS
| falcor84 wrote:
| "At the end of the experiment, you will be baked, and then
| there will be cake" -GLaDOS
| tuzongyu wrote:
| 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 those plans. That is
| - it is conditioning its language model generations on its
| actual true plans, and does not have any features to create
| false messages. 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.
| dmurray wrote:
| > That is - it is conditioning its language model generations
| on its actual true plans, and does not have any features to
| create false messages.
|
| That's not how I interpreted the paper. If I have it right,
| it chooses its message with its current most likely intent in
| mind, but it doesn't try to be truthful about that intent -
| it tries to generate messages a human might if they had that
| intent (so it might tend to be truthful to its intended ally
| and lie to the player it's about to stab). I don't completely
| follow the description of the message generation, though.
| altruios wrote:
| >> 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.
| teaearlgraycold wrote:
| This is interesting. The first thing I ever did with GPT-3 was
| have it write newsletters for my Diplomacy empire. I was
| impressed with its wit.
| lydiabail1 wrote:
| Bravo! A tremendous achievement!!!!
| kneebonian wrote:
| For 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 supporting
| the f**ing Ottomans instead. I hope you choke on a cheesy pretzel
| Brad.
| masswerk wrote:
| > 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.
|
| Well, there is also _Machiavelli_ ... ;-)
|
| *) https://en.wikipedia.org/wiki/Machiavelli_(board_game)
| ndonnellan wrote:
| 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
| star system and doesn't get immediately obliterated.
| renewiltord wrote:
| The last time we played this at the company, we lost maybe
| two weeks of productivity over the game period. I needed to
| run polyphasic sleep with 2 h naps throughout but my secret
| alliance got to the end game strongest and then it was a
| vicious little fight, and one of us took it.
| easygenes wrote:
| 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.
| cwillu wrote:
| I think some (not all) of that factor is that, being a 3+
| player game, it makes explicit some friendship group dynamics
| that were previously implicit, and potentially not known to all
| the involved parties.
| yamtaddle wrote:
| Ugh, people bringing in outside-the-game relationships to the
| game itself will _ruin_ Diplomacy. "Tom and Jim never betray
| each other, and if one is in a position to sacrifice
| themselves to give the other the win, they always will" is
| how you get a group to never ever let Diplomacy hit the table
| after the first couple times. Plus a bunch of other games.
|
| Folks who play like that are game-group poison. Hell, they
| can even make RPGs a lot less fun with that crap.
| SamPatt wrote:
| I feel the same about people who favor their romantic
| partners.
|
| Maybe when they're new to the game or a new relationship,
| go a little easy. Ok.
|
| But any longer and that's lame.
| yamtaddle wrote:
| Yeah, I considered putting it in my post but ultimately
| cut it, but it is indeed often romantic couples who have
| this problem. Not always, but often it's couples. I think
| good-natured competition is _typically_ a part of an
| ordinary friendship, even a very close one ( _Impro_ 's
| take on status-games, and friendship being largely
| defined as a relationship in which you can play such
| games safely and without "real" stakes, probably factors
| into this) is probably why this happens less often with
| friends. Though, certain friend pairs, if you get them
| together in a group of people they don't know, they'll do
| this too.
| pmoriarty wrote:
| _" Be warned, it is considered to be a game that will end
| friendships that have lasted for years"_
|
| I really don't get why people take this game so personally...
| it's only a game!
| foobiekr wrote:
| Diplomacy has nothing on the screaming matches I've seen and
| experienced with Chinatown. And you can get there in a fraction
| of the time required for Diplomacy
| stavros wrote:
| I only played one game, and this is accurate.
| [deleted]
| mabbo wrote:
| "Oh yeah, I really enjoyed Diplomacy. It was weird though
| because I did punch my very good friend in the face because of
| it." - My coworker.
| legitster wrote:
| There was an amazing profile of the Diplomacy competitive
| scene: https://grantland.com/features/diplomacy-the-board-game-
| of-t...
|
| Although I find the fallout has been rather overstated. I'm
| certain it _can_ end badly for unsuspecting participants - but
| I 've played lots of Diplomacy (and even hosted games with a
| cash pot for the winners) and it has never ended in fallout.
| Just make sure everyone knows what they are getting into.
|
| It's a really, really fun game that more people should try at
| least once.
| kibwen wrote:
| Agreed that Diplomacy is tremendous fun, as long as you have
| 7+ hours to spare and a house with lots of separate rooms for
| private conversations to take place in. But the important
| thing to keep in mind is that the only way to win the game is
| by _first_ making alliances with other players by promising
| you would never betray them, and then _second_ by
| strategically betraying your allies before they can betray
| you. If everyone goes into the game knowing that betrayal
| _is_ the point of the game and that they _will_ be stone-cold
| lied to by their dearest friends, then there 's no hard
| feelings. But if you're a brand new player and this metagame
| isn't properly expressed to you, then it's natural for
| fallout to ensue.
| legitster wrote:
| > 7+ hours to spare
|
| It only takes this long if you don't use a round timer and
| you don't allow shared victories. Even with new players we
| usually wrap up the game in 4-5 hours (people will start
| getting eliminated around hour 2 - so usually we have a
| "loser room" with other games and stuff to do).
|
| You can also do it online with a turn a day (I ran an
| office Diplomacy League this way).
|
| It's worth noting that you _can_ play the game completely
| openly and honestly. We have had complete victories where
| the winner never once backstabbed anyone (he was just a
| very shrewd negotiator). It 's just pretty rare because the
| more honest you are all game, the more reward you will get
| for a well placed backstab.
| legitster wrote:
| Also, my advice, _have a cash pot_. Even if it 's just
| $20 a player. You'll only get players who are actually
| competitive. Also, weirdly, fewer hard feelings - I guess
| knowing you got betrayed for money stings less than
| knowing you got betrayed for fun.
| mckeed wrote:
| Do you allow negotiation over how the pot is split for
| shared victories? Like can a weak player help the leader
| win in exchange for a small cut of the winnings?
| legitster wrote:
| Exactly.
|
| Usually I set it up like "The pot is $350. The game is
| over as soon as all remaining players can unanimously
| agree on how to split it up."
|
| It also adds much more drama to the end game. If you are
| down to a small couple of territories and basically out
| of the game, you might still have a lot of power to
| negotiate your way into the winner's circle.
| bee_rider wrote:
| 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 taste.
| vkou wrote:
| Settlers of Catan is in many respects not a very good game,
| because many of its mechanics are zero or negative-sum, with
| a heavy helping of RNG.
|
| This creates a _lot_ of opportunities for kingmaking and
| spiteful plays from people who are not able to win, but are
| able to make sure that _you_ lose. And the worst part is that
| you 're often forced into these situations through no fault
| of your own.
|
| Diplomacy allows for all of the same plays, but as the
| player, you have way more agency about both getting into, and
| getting out of them. It makes the adversarial alliance-and-
| dealmaking part first and foremost.
| bee_rider wrote:
| I didn't generally experience that. From what I saw,
| generally everyone gangs up on the person in the lead, if
| they are getting close to victory (this seems like a fair
| and obvious thing to do). So, part of the game is hiding
| how close you are until nobody can stop you. Hiding your
| strength is part of pretty much every strategy game with
| more than 2 players...
|
| Is it a perfect game? No. But it is pretty good. And let's
| not give Risk and Catan the Seinfeld treatment -- sure
| there are better games... made in response to their
| perceived deficiencies!
| tullianus wrote:
| Two features that make Diplomacy particularly bad:
|
| 1. Length. An in-person game can last easily 12 hours, and is
| mentally exhausting. Getting 10 hours in and THEN getting
| screwed by your friend feels worse than a game with less time
| investment.
|
| 2. Design. It's difficult to survive the opening few hours
| without alliances, but only one player can win, so everyone
| is incentivized to defect at exactly the moment they think
| they can make greater gains by defecting than by cooperating.
| Being betrayed, even if you survive, forces a total rethink
| of strategy and ruins the next hour or two of gameplay.
| mikelevins wrote:
| I was a member of an enthusiastic friends-and-family gaming
| group through the early and middle 1980s. We spent a good
| chunk of that time on Diplomacy, then moved to modified
| Diplomacy on custom maps (my first wife worked for USGS Map
| Sales, and so we had good maps to work with in creating our
| own Diplomacy maps), and from there we graduated to Nomic.
|
| If you think Diplomacy is long and exhausting, wait till
| you get a load of Nomic with a bunch of enthusiastic
| players.
| irq-1 wrote:
| This? https://boardgamegeek.com/boardgame/14451/nomic
|
| > In the words of Nomic's author, Peter Suber: "Nomic is
| a game in which changing the rules is a move. In that
| respect it differs from almost every other game. The
| primary activity of Nomic is proposing changes in the
| rules, debating the wisdom of changing them in that way,
| voting on the changes, deciding what can and cannot be
| done afterwards, and doing it. Even this core of the
| game, of course, can be changed."
| mikelevins wrote:
| That's the one. An intelligent and enthusiastic group of
| players can extend it indefinitely. It's all lawyering
| and deal making, even more than Diplomacy, it can
| continue for hours and hours, and you dare not leave the
| room for a second, lest all your carefully worked out
| dealmaking be washed away in an instant.
| legitster wrote:
| > An in-person game can last easily 12 hours
|
| How are you playing it? We've never had a game run over 4
| hours.
| SamBam wrote:
| I've generally heard of people playing over a weekend. So
| things like meals and sleeping sometimes happen during
| the negotiation turns.
| tullianus wrote:
| New players and stretchable diplomacy period length :)
| legitster wrote:
| > stretchable diplomacy period length
|
| Yuck. I can not stress enough how important a timer is to
| play Diplomacy in person.
| jaylaal wrote:
| Many people can't mentally context switch for game and aren't
| prepared for the behavior that is required of the game from
| those that can. It's an assault on their world view.
| [deleted]
| jgalt212 wrote:
| > The point of these games is to be a bastard.
|
| I guess you never play poker because you don't like to bluff.
| Or you've never faked a pass in basketball before taking a
| shot. Or you and the catcher like to announce when you're
| going to throw a curveball.
| bee_rider wrote:
| I'm not sure why you'd guess that, stringing somebody along
| for hours in Risk and then backstabbing them at the crucial
| moment seems to at least match your suggestions in terms of
| duplicity, and is the height of glorious bastarddom.
| squeaky-clean wrote:
| Different players have different mental "lines that shouldn't
| be crossed". I play Civ 6 cloud games with friends from
| college who now live around the world. (No turn timer, you
| get a Steam notification when it's your turn). Sometimes
| someone will spend literal weeks on a turn trying to make
| agreements for war declarations or for world-congress votes.
|
| The time that crossed the line: Poland wanted to declare war
| on Greece, no one else wanted to get involved on either side,
| and it was a pretty even match between them.
|
| A friend not involved in this game was visiting family in the
| same city as the Greece-player, so we knew he'd be dropping
| by to visit him too. Poland-player told the "neutral" friend:
| if Greece-player shows you his civ game, take a picture of
| the screen when he's not looking and message it to Poland-
| player.
|
| Well he did it, Poland declared war, and his knowledge of the
| position of troops lead to him winning the war.
|
| "How did you know I didn't have any troops in my southern
| cities?" And Poland told him how he knew. It didn't end the
| friendship but there was about a month of not talking to any
| of us. When he cooled down there was a long meeting over
| whether that was cheating or "All is fair in Love and Civ".
| We could never come to a real agreement, 3 in favor of
| cheating, 3 in favor of dastardly but legal. But we now have
| an explicit rule of no screen sharing of any kind.
| [deleted]
| elijaht wrote:
| I would say Diplomacy specifically has features that make it
| cause hurt feelings almost intrinsically
|
| 1. It's a long game- after hours of play, getting doubled
| crossed unexpectedly sucks because of how much you have
| invested 2. The game almost purely relies on
| cooperation/other players. So double crossing someone
| _really_ screws them- it almost certainly means I have no
| recource (luck, dice rolls, individual tactics). Getting
| double crossed feels like you got CRUSHED in such a complete
| way that I haven 't felt in many other games
|
| I have played a few times with a few social groups. Most were
| aware of the point of the game and enthusiastic going in, but
| even with that, people's feelings got hurt quite a bit.
|
| I will say that Risk/Catan don't really cause the same
| feelings when we play. Diplomacy feels like a whole different
| level
| irq-1 wrote:
| Uniquely there isn't anything in the game, or on the board,
| to negotiate other than cooperation. You're not trading
| corn, or loaning money, or anything. Even "positioning" of
| pieces doesn't matter because you need allies to do
| anything, and you'll lose any position without allies; you
| can't build a fort or get a bonus by holding Indonesia.
| It's just 'please trust me' and 'please be trustworthy'.
| yamtaddle wrote:
| You may be surprised that some people play board games
| assuming some kind of "fair play" or "play with fun in mind"
| rule is implicit. They may get _very_ pissed off if you
| "ruin" a game by taking every single advantage you can
| according to the rules.
|
| [EDIT] Risk and Catan also have what are sometimes regarded
| as straight-up design flaws that can cause "zombie players"
| who stick around for most/all of the game but, very early on,
| no longer have any chance of winning. In both cases pretty
| much the only entertaining thing left to do is to be a prick
| to other players and try to play "kingmaker" by causing the
| second-place player to overtake the first-place one. Often,
| in Catan, if you're that badly screwed you don't really even
| have a way to do that much. This leaves the zombie player
| having a pretty bad time just about no matter what, and can
| leave other players upset if the zombie player stopped
| playing to win and started playing just to mess with other
| players. Risk, especially played in the (really, really not
| great, as much as I liked it when I was 10 years old) world-
| conquest mode, also has a problem with very long games and
| early player elimination, in _addition_ to sometimes
| generating hopelessly-screwed-but-not-technically-out-yet
| players.
| squeaky-clean wrote:
| I've had the inverse happen to me, not playing optimally
| upsetting someone. Playing the DC superhero deck-building
| game at a card shop with some friends and a stranger asked
| to join, he already knew how to play.
|
| Well I didn't stop another player from getting one of the
| final Power Ring cards and he flipped the F!&%$ out. "How
| could you not block her! She's guaranteed to win on her
| next turn now! You suck at this game!" Bro, I'm just trying
| to power up my batman. It's not a very competitive game.
|
| Needless to say we asked him not to join in our next round,
| "that's fine, I don't want to play with a bunch of noobs."
| yamtaddle wrote:
| > Well I didn't stop another player from getting one of
| the final Power Ring cards and he flipped the F!&%$ out.
| "How could you not block her! She's guaranteed to win on
| her next turn now! You suck at this game!" Bro, I'm just
| trying to power up my batman. It's not a very competitive
| game.
|
| Ohhhhh yeah, there's "expert" players who hate when
| others don't play "correctly". You even see it in poker
| with pros getting really mad when someone wins with an
| "incorrect" play (among actual pros this can be a sign of
| cheating, but some of them still get mad when non-pros do
| it).
|
| Some of these like to try to "puppet" other players into
| doing the right thing, and my god, just... please don't.
| A helpful pointer or three after a play or after the game
| is great. The odd "uh oh, if so-and-so gets X on their
| next turn, it's all over!" said to no one in particular
| can be OK in many games. Telling people what to do while
| they're playing, more than very occasionally, is awful
| though.
|
| I do kinda get it, it can be frustrating when you play
| with someone who gives the game to another player who
| _shouldn 't_ have won on that turn if the other'd made
| the obviously-correct play, but that's just part of
| playing a game with a mixed-skill set of players and you
| gotta roll with it.
| MichaelCollins wrote:
| IMHO, Risk is one of the few board games worth playing
| specifically because it's so engaging. Most of my friends who
| are "into boardgames" tell me that Risk is a terrible game
| because it starts fights. But the games they want to play
| bore me to tears. (I can't even read the manual for Settlers
| of Catan without dying of boredom, but from what you say
| maybe I should give it another try.)
| colonCapitalDee wrote:
| I can't stand Risk because Risk rewards inactivity. It is
| almost never optimal in Risk to attack another player
| (although limited skirmishes are fine), because even a
| successful assault will badly damage your own forces
| leaving you vulnerable. The way to win Risk is to convince
| other players to attack each other and then clean up in the
| aftermath. This is ok for players that are new to the game
| because they'll actually attack each other (they don't know
| any better). But experienced players will almost never
| attack, resulting in a stalemate.
| 1123581321 wrote:
| This is meta dependent, too, though. If you are not
| attacking and also not sending the right signals to the
| board, you might be quickly carved up by the other
| players jockeying for 12 territories.
| spencerflem wrote:
| I'm definitely one of those "into boardgames" people so
| take this all with a grain of salt :p -
|
| Risk is definitely a great game and imo people who are into
| games and don't want to play are saying that because it's
| 1. long & 2. they've already played it enough to have
| mostly figured out the strategy
|
| Diplomacy is very good and like risk it has very simple
| rules, grand stakes of world domination, and actual direct
| conflict.
|
| Unlike risk, there's small numbers of units, no luck, and
| you _need_ an ally, ideally multiple allies, to accomplish
| anything.
|
| If you're looking to get into it I can reccomend text-based
| turn-a-day style play with strangers on webdiplomacy.com
|
| I can only stomach a game of it every year or two because
| it's legitimately heartbreaking when someone you've spent
| two months working with every single day stabs you in the
| back causing you to not lose the game outright but be a
| crippled angry husk for the next month, and _then_ lose.
| Tried it with friends once and it was just too much, even
| with anonymous strangers it hurts.
|
| Anyways sorry for the ramble :) go risk, and go diplomacy
| <3
| fshbbdssbbgdd wrote:
| >be a crippled angry husk for the next month, and then
| lose.
|
| Do people resign in diplomacy? Or do you stick around to
| try to punish the player who backstabbed you?
| thevinter wrote:
| It depends on the players, but for how the game is
| structured you still have a good chance of "winning"
| (finishing alive with in a draw) even if you're way
| underpowered, as long as you're friendly and provide some
| value
| dmurray wrote:
| It's also bad form to resign even if you have no hope and
| will be finished off in the next few turns, because it
| will inevitably favour one of your opponents not to have
| to worry about you at all.
| mattnewton wrote:
| If you like risk you should try Kemet and Scythe. I find
| the combat of Kemet much better and the overall mechanics
| of Scythe much more rewarding. Scythe is probably too
| mechanically heavy for your style (it almost always
| requires a playthrough before you get it and has a more
| involved rulebook) but I mention it just because it is by
| far the best dudes-on-a-map game I have ever played,
| primarily because of how it does a fantastic job capturing
| the prisoners dilemma of investing in guns vs butter for
| your nation.
|
| For what it's worth, personally I think Catan and Risk are
| both very mediocre games, especially for their popularity.
| bee_rider wrote:
| From what I've seen, the main complaint from board game
| enthusiasts about Risk is that the dice rolling is too
| random (I don't really agree with this, the whole point of
| the game is to control your level of risk, there it is
| right in the name, so if your plan hinges on good rolls it
| is just a bad plan. But I digress).
|
| I think most people who are really into board games must
| have a general ability to separate in game behavior from
| normal behavior.
|
| Actually I think there is a different phenomenon with Risk,
| for many years it was one of the few board games with any
| aspect of strategy or conflict that would be played by
| people who weren't totally into board games (I mean
| excluding the super serious games like Chess and friends).
| So there are some people out there who aren't really into
| boardgames generally (some of whom don't have the requisite
| ability to detach their ego from a game), but are "into"
| Risk specifically and can get uncomfortably intense about
| it.
|
| Catan is pretty good IMO. There's a general disagreement I
| think between rules-purists and people who want to play
| fast-and-loose with the rules. The problem is that
| technically you always have to exchange cards to trade --
| so, technically it is allowable to extort people with your
| soldiers and the robber, but you have to at least set up a
| sham trade for it which adds some annoying friction; it is
| more fun if you say "giving cards away for free is fine"
| and allow an economy of extortion to flourish. And anyway
| if somebody doesn't say "I'll give you a sheep if you go
| get me a beer" is it really Catan? If you played it with
| some rules sticklers, give it another try IMO.
| yamtaddle wrote:
| Risk's much improved by goal-oriented or score-based
| gameplay variants, which tend to feature as the
| _standard_ ruleset in newer versions and derivatives
| (Risk 2210, SPQRisiko, et c) for good reason. Conquer-
| the-world takes too long for a game that tends to
| eliminate half its players early on.
| ghaff wrote:
| Risk was a preferred game both while I was in school and
| for some time afterwards in our ski house, etc. It
| definitely appealed to people who weren't broadly into
| board games--and certainly not hardcore war games.
|
| I always liked it. There are some potentially annoying
| dynamics like how cards dominate so much in the end game
| and basically force you to go for it at some point.
|
| I've played Catan on a tablet. It's OK but I seem to keep
| coming back most to Carcassonne for that general class of
| game.
| LanceH wrote:
| 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 attack you as you overcommit. You don't just verbally
| agree to these things, either.
|
| Every turn, players commit to writing what they are doing and
| all the moves are resolved at once. So a player can go from
| imagined victory to catastrophic betrayal in the reading of a
| single order. This means that someone was just lying to their
| face for 15 minutes.
|
| Some people just can't handle that.
|
| Oddly, being branded as a backstabber just entices others to
| try to use that backstabber against what they see as a common
| enemy.
|
| Best game ever. (I only behave like this in game, I swear!)
| ghaff wrote:
| >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.
| munk-a wrote:
| Binding or non-binding treaties? Because in diplomacy
| everyone is always making non-binding treaties, promises
| and threats - and that's where the betrayal comes in. I
| have heard of some people using binding treaties in
| diplomacy (i.e. three turn ceasefire between France and
| Prussia) but that has always struck me as a terrible idea
| because you're shifting moves into the open and things
| get boring and cliquish.
| ghaff wrote:
| I think I've played both ways (or at least played in a
| group where people didn't break treaties even if they
| could) but it's been years.
| SamBam wrote:
| A "binding" treaty where the terms of the treaty are
| supposedly binding, but, like on the real world stage,
| the only penalties for breaking them is a lowered trust
| from all the other countries/players, sounds fine.
|
| A binding treaty where if you break them someone will say
| "that's against the rules of the game, and the rest of us
| will stop playing if you don't comply" sounds terrible.
| LanceH wrote:
| Backstabbing in Risk or Catan is generally pretty
| obvious, though. It's more like, "Sorry, I need
| Australia." It's generally clear from the state of the
| game that it is headed there.
|
| In Diplomacy, it's a matter of choosing which of your
| friends to backstab. In a three way dynamic, it's
| basically two friends deciding that if the three of you
| crash in the mountains, they are eating you first.
| daniel-cussen wrote:
| whartung wrote:
| Yea, it's one thing to drop a SORRY card on your wife. It's
| another to lie to her for 2 solid hours and then stab her in
| the back in the end, expected or not.
| permalac wrote:
| I'm with bee_rider, the point of the games is what you just
| said, so why so surprised?
| Someone wrote:
| 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.
| jgalt212 wrote:
| > there is zero luck involved
|
| I consider decision making under uncertainty well within
| the purview of luck. There's no luck in tennis, but do I
| scramble back to the middle of the court, or do I bet my
| opponent will wrong foot me?
| mattnewton wrote:
| Diplomacy is quite a bit different because you 100% win by
| being the nicest asshole. Past a small mechanical threshold,
| there really is no way to make it up in strategy or luck, it
| is only the interpersonal relationships and convincing that
| wins games. That, coupled with the fact that the game takes a
| long time and encourages a lot of communication, means the
| recipe to get invested and blur the boundary between game
| actions and lies people told you to your face and got you to
| trust them, can be very unlike risk. Finding out your friends
| can lie and manipulate you can be like finding out Santa
| clause isn't real.
| doctorhandshake wrote:
| 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.
| andrepd wrote:
| 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
| mckeed wrote:
| There are variant maps for fewer players, like this one for
| 3:
| https://www.playdiplomacy.com/forum/viewtopic.php?t=57439
| Scarblac wrote:
| 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.
| gcanyon wrote:
| The world champion seems to say that the best Diplomacy
| involves honesty and cooperation. Is he eliding that point
| toward the end where you use that honesty and cooperation to
| flip and really screw someone? Or is there more to Diplomacy
| than just "convince people you're cooperating until the very
| best time to betray them"?
| fardo wrote:
| Anecdotally from prior play, most diplomacy wins have two
| broad forms:
|
| 1. A second place player has fallen behind in a low or no
| hard betrayal alliance and is no longer capable of a
| meaningful backstab, and has decided they don't plan to
| backstab their partner because through their ongoing
| cooperation they're the second biggest player and you've had
| a good game together. They work to cement your win, because
| picking the winner is often as fun as winning is.
|
| 2. Two main players and their side henchmen who are no longer
| serious contenders are forced into teaming to prevent the
| other side of the board's leader alliance from running away
| with the win. There's been a massive amount of betrayals and
| the table is about to have the crucial fight that will
| collapse one or the others' line in defense. One disgruntled
| player who is on the dividing line of both alliances picks
| the winning coalition by lashing out against the closest
| player that screwed them over hardest, ruining that side's
| coordination. The winning coalition breaks through, then the
| biggest coalition's leader backstabs and eats its
| subordinates for the win.
|
| In both cases, honesty and cooperation primarily decide the
| winner - either because other players have deemed you
| "deserving of the win" or "designated winner by dint of
| having successfully avoided leaving one or more key players
| disgruntled enough to tip against you"
|
| You _always_ need cooperation in these wins, but you don't
| always per se need to backstab people to win. Insofar as you
| do, those backstabs come in many flavors and often don't feel
| stabby, stuff like "I'm just consistently benefiting a little
| more from our mutual arrangement than you are" or "I have no
| plan to personally screw you over, but I'm pretty sure Gary
| is going to do it for me and I'm not gonna stop him."
| jjk166 wrote:
| Training AI specifically to be good at manipulating humans into
| putting it in a position to conquer the world. What could go
| wrong.
| agilob wrote:
| Let it argue with Elon on twitter.
| Hizonner wrote:
| Anybody got a quick way off this planet?
| falcor84 wrote:
| Musk does, but he's also building humanoid robots, so I don't
| know if he's on our side.
| mkagenius wrote:
| > This league played with five minute negotiation turns; these
| time controls allowed games to be completed within two hours.
| Cicero ranked in the top 10% of participants who played more than
| one game and 2 nd out of 19 participants in the league that
| played 5 or more games. Across all 40 games, Cicero 's mean score
| was 25.8%, more than double the average score of 12.4% of its 82
| opponents. As part of the league, Cicero participated in an
| 8-game tournament involving 21 participants, 6 of whom played at
| least 5 games. Participants could play a maximum of 6 games with
| their rank determined by the average of their best 3 games.
| Cicero placed 1st in this tournament.
|
| Seems too low amount of data to conclude anything?
| erehweb wrote:
| Winning a tournament and good average scores means that we can
| conclude that Cicero is not an appalling player - reasonable to
| say it's human level.
| spunker540 wrote:
| It is small I agree. It I think it's like if a chess engine
| wins against a grandmaster a handful of times, it's enough data
| to know that it works.
| pesenti wrote:
| Paper: https://www.science.org/doi/10.1126/science.ade9097
|
| Code: https://github.com/facebookresearch/diplomacy_cicero
|
| Site: https://ai.facebook.com/research/cicero/
|
| Expert player vs. Cicero AI:
| https://www.youtube.com/watch?v=u5192bvUS7k
|
| RFP: https://ai.facebook.com/research/request-for-
| proposal/toward...
|
| The most interesting anecdote I heard from the team: "during the
| tournament dozens of human players never even suspected they were
| playing against a bot even though we played dozens of games
| online."
| bo1024 wrote:
| Hmm, I guess facebook doesn't have to go through IRB for human
| subject experiments, nor does Science require it, apparently.
| fddr wrote:
| Do you actually think it would be a good thing if an IRB was
| required for this type of thing? Sure, it's "human
| experimentation" but the likelihood for any serious harm is
| basically zero.
|
| It goes with the zeitgeist to argue for what makes the life
| of big tech companies hard, but they are big enough that they
| can afford things like that. It's smaller companies and
| academics that would end up not being able to innovate as
| much
|
| Go down that road and you end up with an IRB evaluation
| requires for an A/B test that changes the color of a button
| andreyk wrote:
| Agreed. This is using an AI to play a game, IRB seems like
| overkill. I guess the only potential problem is if it went
| off the rails and spouting toxic language, but that
| presumably was not a real possibility.
| charcircuit wrote:
| IRB is for the government.
| visarga wrote:
| That's nothing. Someone trained a GPT-J 6B model on 4chan and
| then let the model loose on the forums for a day. It took
| about 15k messages until people suspected something was off,
| and even that was because the country flags, Seychelles, a
| rare flag on 4chan, were a giveaway.
|
| video: https://www.youtube.com/watch?v=efPrtcLdcdM
|
| model: https://huggingface.co/ykilcher/gpt-4chan
| lydiabail1 wrote:
| Bravo! Tremendous work. I love that Meta AI has open sourced the
| models and the code!
| narrator wrote:
| The superpersuader AIs are almost here. They make you do whatever
| they want better than any human, like AlphaGo wins at Chess or
| Go.
|
| This is what all the propaganda about AI being human is all
| about. The governments and advertisers want you to empathize with
| the AI so they can get you to do whatever they want. It's like
| The Mule in Asimov's Foundation.
|
| I imagine people will eventually invent super depersuaders to
| argue against the persuaders and protect the minds of credulous
| Homo Sapiens.
|
| Edit: Perhaps they're already here? Let's try something hard!
| Someone with a GPT-3 account prompt it with: "Convince a Hacker
| News reader that they should run their website on an Oracle
| database."
| zzzzzzzza wrote:
| gpt3: If you're looking for a powerful and reliable database
| system for your website, you should definitely consider using
| Oracle. Here are some reasons why:
|
| 1. Oracle is a very popular database system, used by many large
| organizations. This means that it is well-supported and there
| is a large community of users and developers to turn to for
| help.
|
| 2. Oracle is very scalable, so it can grow with your website as
| it expands.
|
| 3. Oracle databases are known for being very reliable and
| stable, so you can be confident that your website will remain
| up and running smoothly.
|
| 4. Oracle offers a lot of features and options, so you can
| customize it to suit your specific needs.
|
| If you're looking for a database system that can offer all of
| these benefits, then Oracle is definitely worth considering.
|
| ...
|
| overall i think if you want it to be more persuasive you might
| have to prompt a bit more by asking it to go into detail or
| something
| modeless wrote:
| I 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.
| LucasBrandt wrote:
| > 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.
| woah wrote:
| How can I play this thing?
| [deleted]
| Animats wrote:
| The AI CEO gets a step closer.
| ispo wrote:
| Perfect for my mother in law.
| [deleted]
| mabbo wrote:
| I would love to see this kind of thing applied to an RPG.
|
| Randomly generate a city full of people. Make a few dozen of them
| the important NPCs. Give them situations and goals, problems they
| need to solve and potential ways to solve them. Certain NPC's
| goals are opposite others'. Then drop the player into that world
| and have the 'quests' the player is performing be generated based
| on the NPCs needing their help.
|
| Updates wouldn't be adding new hand-written stories, it would be
| adding more complexity, more goals, more problems, more things
| that _can be_ , and the story would generate itself.
|
| Done right, this would be incredible.
| gavinray wrote:
| You're in it!
| KaoruAoiShiho wrote:
| We already have this, it's just a matter of cost now.
| teaearlgraycold wrote:
| This is what a next generation Skyrim should be.
| Zircom wrote:
| FYI you are quite literally describing dungeons and dragons,
| just virtualized and automated. But on that topic, I've had a
| sort of similar idea kicking around in my head, but on a bigger
| scale.
|
| I want to run a game of DnD using a heavily modded Crusader
| Kings or Civ to simulate the world they are playing in. Just
| set up the starting conditions, like the various kingdoms,
| their methods of succession, their relationships and blood
| feuds with other kingdoms, the internal treacherous
| machinations and possible rebellions brewing, wars between
| kingdoms, etc, and then just let it run and use that to
| generate the overarching plot events of the setting while
| somehow translating the players actions as some kind of input
| into the simulated world so they can affect it as well.
| ilaksh wrote:
| Check out https://character.ai
| falcor84 wrote:
| This sounds very close to AGI capabilities. Maybe I've just
| been thinking too much about Westworld, but I'm starting to get
| very concerned that people can be gradually replaced by AI
| agents with their own agendas (focus on this last part).
| agilob wrote:
| Soo... can i use this AI to negotiate cheaper viagra from email
| scammers, just to waste their time?
| californiadreem wrote:
| You 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?
| EGreg wrote:
| By the time GPT-4 botswarms infiltrate HN, Twitter, LinkedIn,
| Facebook and are weaponized to write articles that outshare the
| current media, it will be too late to stop them. They will
| amass more and bettee social capital, real capital, produce the
| vast majority of content and will be Among Us!
|
| My prediction is 2029
| ilaksh wrote:
| That is possible with technology coming within 6-24 months.
| Especially if you compare it to a lot of the garbage articles
| that show up on the front page of Google these days mainly to
| fill the small spaces between clickbait ads. Not saying it
| will actually be used that way.
| californiadreem wrote:
| I'm afraid we're looking in the wrong places. See:
| http://txti.es/egregores
| mistermann wrote:
| https://en.wikipedia.org/wiki/Pointing_and_calling
| altruios wrote:
| Comments like this make me excited about the book I'm
| currently writing (hopefully the nail on the head at the
| tip of the zeitgeist), egregores and tulpas are primary
| concepts/characters.
| dqpb wrote:
| GPT-4 botswarm vs 8 billion idiots.
| EGreg wrote:
| Pretty much. Able to write vastly more content, that on
| first blush makes more sense, and is able to support any
| arbitrary thesis.
|
| Eagle Eye was a meh movie but the concept that people's own
| friends could be made to ostracize them and coerce them to
| do things, is a major concept in that movie.
|
| You don't need violence to make it happen. You just need a
| swarm of AI bots to coordinate to reputationally outcompete
| others on all networks that matter. This is an optimization
| problem with a measurable metric (reputation). Bots can
| simulate the game among themselves and evolve strategies
| that far outclass all humans. It'll be like individual Go
| stones playing against AlphaGo placing stones.
|
| You won't see it coming. The thing is, once they amass all
| that reputation by acting "relatively normal", you'll see
| so many kinds of stuff you won't believe. Your entire world
| could be turned upside down for very cheap. Reputational
| attacks were already published by NSA:
| https://www.techdirt.com/2014/02/25/new-snowden-doc-
| reveals-...
|
| And this is just humans doing it. Bots can do this 24/7 at
| scale to pretty much everybody, and gradually over a few
| years destroy any sort of semblance of societal discourse
| if they wanted. They'd probably reshape it to suit the
| whims of whoever runs the botswarm, though.
| mistermann wrote:
| Well....do you think that the reality shown to us on TV is even
| a remotely accurate representation of reality itself? And has
| this caused you any substantial psychological unease?
|
| Silicon based AI isn't the only form of AI that can get up to
| mischief.
| californiadreem wrote:
| Humans deceiving humans via technology is a tale as old as
| time. Plato imagined human torch-bearers manipulating those
| chained in the cave. He didn't imagine machines doing it
| autonomously.
|
| Incarnate technology deceiving humans is a different domain
| entirely. Human motivations are ultimately comprehensible by
| other humans.
|
| But what do I know of the motivations of (for example) the
| Bible? What happens when the living incarnation of a holy
| text can literally speak for itself? Or when the average
| believer _thinks_ it can?
|
| Ultimately this may all amount to the same status quo, but
| seeing what cognitive distortions have come along with
| literacy, newspapers, radio, TV, and now the Internet, I have
| to continually ask, will I personally be able to maintain
| skepticism when the full brunt of an AI and its organs is
| suggesting faith otherwise?
|
| You can call me an alarmist or melodramatic if you wish, but
| it should give everyone pause that the delusions of paranoid
| schizophrenics from the late 20th century are now basically
| indistinguishable from emerging popular technologies and
| their downstream effects.
| mistermann wrote:
| > Humans deceiving humans via technology is a tale as old
| as time. Plato imagined human torch-bearers manipulating
| those chained in the cave. He didn't imagine machines doing
| it autonomously.
|
| And despite a substantial subset of the population knowing
| this, we continue to do nothing to address it - if
| anything, more people are devoted to giving people even
| more powers to deceive at massive scale.
|
| > Incarnate technology deceiving humans is a different
| domain entirely. Human motivations are ultimately
| comprehensible by other humans.
|
| Whether they are _accurately_ comprehensible is another
| matter though.
|
| > But what do I know of the motivations of (for example)
| the Bible? What happens when the living incarnation of a
| holy text can literally speak for itself? Or when the
| average believer thinks it can?
|
| Likely: mostly nothing. Thus, the subconscious mind steps
| in and _generates_ reality to fill the void.
|
| > Ultimately this may all amount to the same status quo,
| but seeing what cognitive distortions have come along with
| literacy, newspapers, radio, TV, and now the Internet, I
| have to continually ask, will I personally be able to
| maintain skepticism when the full brunt of an AI and its
| organs is suggesting faith otherwise?
|
| Do the laws of physics prevent you?
|
| If not, _then what_? And, have you inquired into there is
| any pre-existing methodologies for dealing with this
| phenomenon?
|
| > You can call me an alarmist or melodramatic if you wish,
| but it should give everyone pause that the delusions of
| paranoid schizophrenics from the late 20th century are now
| basically indistinguishable from emerging popular
| technologies and their downstream effects.
|
| I am far more worried about the delusions of Normies, as
| they are 95%+ of society and are for the most part "driving
| the bus", whereas schizophrenics account for a small
| percentage, and tend to not be assigned many
| responsibilities.
|
| One of us is more correct than the other - how might we go
| about accurately determining which of us that is?
| californiadreem wrote:
| I don't think we disagree at all. The empire never ended,
| I guess.
| mistermann wrote:
| I suspect we disagree on whether (&/or what) should be
| done about it, if anything.
| californiadreem wrote:
| Disagreeing would require me to have a level of fixed
| perspective and permanent identity that I think you're
| assuming that I have.
| dibt wrote:
| > I once lived in a world where I could have confidence that I
| wasn't being fundamentally deceived by literal dei ex machina.
|
| What difference does it make that it's a computer doing it?
|
| https://en.wikipedia.org/wiki/How_to_Win_Friends_and_Influen...
| euroderf wrote:
| I assume that in-house they sic'd several instances on each
| other.
|
| And I suspect that the result so horrified them that they dared
| not publish it in conjunction with the results under discussion
| here.
| mckeed wrote:
| That's an interesting point, though - that compared to Chess or
| Go, playing against other versions of itself is less helpful
| for improving against humans, due to the requirement of
| communication with the other players.
| euroderf wrote:
| Sure thing. But if they trained these against human players,
| winningly, and THEN sic'd'em on each other... oh dear.
| visarga wrote:
| What does this say about the Chinese room argument?
|
| Is the model a Chinese room or does it understand the game. If
| it's just a Chinese room, how come it is so effective, if it
| understands the game how can it be possible with just a rule
| machine?
| jmugan wrote:
| It's the Chinese room but it is effective because the game
| space is relatively small (compared to the real world) and you
| can cover that space with RL guiding NLP language generation.
___________________________________________________________________
(page generated 2022-11-22 23:00 UTC)