[HN Gopher] Conversational Game Theory
___________________________________________________________________
Conversational Game Theory
Author : hoofish
Score : 113 points
Date : 2024-11-28 07:23 UTC (15 hours ago)
(HTM) web link (aikiwiki.com)
(TXT) w3m dump (aikiwiki.com)
| pmontra wrote:
| There is a 77 minutes video in the Project Reviews page from the
| menu of the left. Maybe there is a demo in there but I didn't
| bother to check. It's conversational, it's text based, why didn't
| they include a textual demo in a page?
| totetsu wrote:
| parley.aikiwiki.com. ?
| pmontra wrote:
| That's a static page with underlined text that are not links.
| Does anything interactive start after "Login With Google"
| (that I won't press) ? Anyway, my point is that they should
| have presented the transcript of at least one round of the
| process and demonstrate the improvement it produces. It's
| much less time consuming for a reader that does not want to
| invest hours in videos or actually taking part of the
| experiment. On the other side, those readers might not be of
| interest to the authors so this is a way to let them go.
| hoofish wrote:
| thx for feedback. wasn't expecting such a big response.
| project is in stealth mode
| hoofish wrote:
| Well if you want to sign in, or repeat our steps, or try
| CGT for yourself, just let me know
| QuadmasterXLII wrote:
| Is there an exposition of the ideas and results of conversational
| game theory in the format and authorial style of an academic
| paper? Even if there is no intention to submit it to e.g.
| neurips, creating and prominently linking to such a pdf could
| help not only to refine the ideas but to communicate to
| outsiders. The linked website takes a while to get to the point
| and filled up my crank-o-meter before I got answers to basic
| questions like "what loss are the agents trained on" or "what do
| you think the equilibrium of this game is and why do you think
| that." The field has settled on the (paper, github, blog post)
| link triplet for good reason.
| azath92 wrote:
| I would also love some more traditional explanation of the
| ideas. My impression is the author is operating outside "the
| field", in a traditional academic sense, whether you are
| referring to AI/ML or game theory research. I had a bit of a
| search for citations or other mentions of their 9x3 nerrative
| logic or Conversational Game theory and only found their own
| sites (in a few different places
| https://bigmotherdao.com/f-a-q/, parley.aikiwiki.com) or an
| article under some contention by the author themselves on
| RationalWiki https://rationalwiki.org/wiki/Rome_Viharo. The
| mentioned professor James H. Fallon doesn't appear to have
| clear links to project outside of what is stated in the
| article.
|
| My crank-o-meter (great phrase) overflowed at this point, but I
| am also genuinely interested in some kind of more clarity
| around the ideas, or where they came from in an academic legacy
| sense, as they felt like they might have some interesting
| bones.
|
| Maybe someone with stronger google foo can find more, or
| confirm absence?
| hoofish wrote:
| thx for feedback. project is in stealth mode. always a good
| idea to be skeptical.
| hoofish wrote:
| Yes, this has been an independent project for many years, but
| has had many endorsements from computer science to cognitive
| science. This project has had no problems attracting
| attention and interest from many qualified people, and if you
| want to see how strong the bones are, just ask for a demo, or
| watch the demo on the site. It's probably not best to just go
| off of your first reaction, which seems a little tense and
| aggravated.
| waveBidder wrote:
| I'm surprised something where the crankmeter goes off so
| strongly made it to the front page.
| hoofish wrote:
| i think natural skepticism is a good idea. This is an
| independent project outside of academia, some think that
| projects outside of academia are crank projects by default,
| comes with the territory. Project should be judged on its own
| merits. This is just a stealth site.
| waveBidder wrote:
| I agree, but this is obvious crankery.
|
| > Perfect conversations are made possible through
| Conversational Game Theory.
|
| this is not the sort of thing someone who has thought
| critically about their own work says.
| hoofish wrote:
| You have a very narrow way of conducting a review :)
| hoofish wrote:
| Ummm, clearly it is! Why does something have to be cranky
| just because you don't understand it? Maybe that's on
| you, dude.
| mistermann wrote:
| Relevant:
|
| https://en.m.wikipedia.org/wiki/Direct_and_indirect_reali
| sm
|
| https://en.m.wikipedia.org/wiki/The_Scorpion_and_the_Frog
| hoofish wrote:
| Hi, thanks for feedback. Project is in stealth mode at the
| moment, I was not expecting the response.
| refulgentis wrote:
| Yes, you were expecting a response. I checked who submitted
| it: it is you!
| hoofish wrote:
| Wow, you're clever. Like I said, I was not expecting such a
| response,duh, of course I was the poster. over 5k visits to
| the site. I think the layer of suspicion you put on
| everything is kinda ridiculous.
| nomilk wrote:
| Quite like the desktop website. Feels like a pdf without the
| cruft.
| executesorder66 wrote:
| What is a "desktop website"?
| nomilk wrote:
| Desktop, as opposed to mobile. (on mobile the site looks
| pretty similar to most others). On desktop it feels like a
| pdf, but extremely light weight (in a very nice way; loads
| quickly, scrolls perfectly [unlike pdfs], and isn't
| cluttered). Just a crisp experience.
| executesorder66 wrote:
| Ah I understand now. Thanks.
| samirillian wrote:
| Once again an entirely backwards, upside down perspective. On
| Twitter he called politics the easiest job in the world.
|
| Xenophon said that man is the hardest animal to tame. And the
| author's "make AI great again" mentality is a perfect example of
| this untameability.
|
| If it's not actual AGI don't tell me how a tool can actually fix
| the problems it creates. It's like the author doesn't have the
| most basic concept of what a tool is.
|
| Anyway happy Thanksgiving to the Americans
| upghost wrote:
| Cheers, friend! Thankful for HN and all the great perspectives
| from around the world. Also thanks for the phrase "Make AI
| Great Again"! :D
| hoofish wrote:
| I think you have a misunderstanding, but you are welcome to
| believe your first reaction to something you are not familiar
| with!
| 8BitArmour wrote:
| Isn't game theory suitable only for places where all the actors
| make rational decisions?
| pkoird wrote:
| Well, strictly speaking, it is suitable for places where all
| actors make choices in ways we can predict. So even if an actor
| was choosing, say, uniformly at random (and we knew this fact),
| we'd be able to incorporate it into analysis to get some
| expected behavior.
| kouru225 wrote:
| Yea, and so IMO this idea makes sense if you assume that bad
| conversation is predictable conversation (this is a
| simplified way of saying this but this idea was formalized
| within the field of literary theory by a man named Wolfgang
| Iser as a response to the issue of the hermeneutic circle and
| the merger of horizons). A conversation is evolved to its
| best possible outcome when it encourages the human in the
| loop to face their preconceived assumptions about the world
| and _effectively_ do the work to come to their own
| conclusions rather than act as a follower
| w10-1 wrote:
| But game theory also presumes a closed, on-the-record world.
| E.g., it doesn't handle dumping (loss as strategic gain)
| without opening the scope of game, but there are no scope
| bounds since value of any type is exchangeable (land for
| peace...). So game theory like newtonian physics only helps
| in narrowly constrained systems, but none of the real systems
| where help is needed are so constrained (banking laws
| notwithstanding).
| hoofish wrote:
| That is in classical game theory, in CGT, it is assumed the
| actors are both rational and irrational
| elif wrote:
| It seems like the AI decision making is 'immutable' but in the
| end it will always come down to training data
| upghost wrote:
| this is a so-often overlooked point.
| noduerme wrote:
| It's worse than that. The entire notion of an independent
| arbiter is deceptive at best, because the decision making will
| always come down to how the questions are framed.
|
| The claim here is that an automated process backed with enough
| data and computational power can distill any of the world's
| most intractable conflicts and come up with a compromise immune
| to "toxicity" and human bad-faith. I'd submit that in any
| conflict in which at least one actor is acting in bad faith to
| begin with, in the absence of an overriding ethical framework,
| any such compromise would result in a worse outcome than making
| a decision that one side was right and the other wrong. It's
| the compromise between hens and wolves.
| hoofish wrote:
| In CGT, there is no third party arbitrator, no admin, the
| resolution is reached player to player. thx for response
| w10-1 wrote:
| If/since the universe of human bad faith is finite, it does
| seem possible (and useful) to detect all such forms in
| transactions that are on the record.
|
| This won't solve out-of-band corruption and might indeed
| increase its value, and hence increase the value of
| participating in a corruption network.
|
| gosh darn unintended consequences...
| hoofish wrote:
| You're really way out of left field. You are welcome to a
| live demonstration of how CGT works.
| hoofish wrote:
| in CGT, humans make the final decisions, it is a game designed
| for humans first, AI just came later
| hoofish wrote:
| No, that is a misunderstanding. No third party or no AI, or AI
| training data, is used to arrive at a consensus decision,
| humans have over-ride in the system.
| zug_zug wrote:
| I'm having trouble understanding all the upvotes for a wall of
| buzzwords from across-fields. Would love to understand what this
| even is in plain english if somebody has the time.
| hoofish wrote:
| thx for response. I think it is pretty straight forward on the
| site. project is in stealth mode. "Conversational Game Theory"
| is pretty straightforward.
| cowpig wrote:
| Stealth mode project that is publishing whitepapers to HN and
| replying in comments about its stealthiness?
| Mtinie wrote:
| Double-secret misdirection. The new stealth!
| hoofish wrote:
| I think it is silly to load everything up with so much
| suspicion.
| hoofish wrote:
| yes, i often seed on social media as the project evolves to
| get feedback.
| hoofish wrote:
| The company is in stealth mode, thanks for clarifying.
| lugao wrote:
| Exactly! And it was obviouslly written by (or with help of) a
| LLM. The first definition is even gramatically incorrect! Lets
| see what gemini thinks of the first paragraph if I force it to
| criticize it:
|
| https://g.co/gemini/share/97c1d475aae1
| ASalazarMX wrote:
| Besides the obvious irony of criticizing a suspect LLM work
| and then asking another LLM to criticize it to prove it, your
| question was loaded:
|
| "Explain why this paragraph is contrived and grammatically
| incorrect: [..]"
|
| Current LLMs are trained to follow your leash.
| Asraelite wrote:
| I don't see any grammatical errors, just some possible
| missing punctuation. The arguments Gemini gives are just
| opinions about stylistic choices. Could you point out the
| specific grammar mistakes you see?
| hoofish wrote:
| These are just grumpy posters, while I was not expecting
| the post to get all of this attention, its usually the ones
| who are reactive or trolling who respond here. They want to
| find so many mistakes just so they don't have to admit to
| themselves that they don't understand what the project is
| or how it works.
| mistermann wrote:
| You've taken this ubiquitous phenomenon into account in
| the design I hope?
| hoofish wrote:
| Our entire system is trained on LLMs, so yes LLMs are used to
| write summaries. Thanks for the feedback.
| bongodongobob wrote:
| Now ask it why the paragraph is well written.
| sdwr wrote:
| It's saying, "AI needs consistent, scored rules for
| communication, so it can self-train being a person the same way
| it self-trains winning games of Go" (sure).
|
| Then it says "we have those rules" (they don't) "and they work
| great" (they don't) "and you can't see them" (sure).
| hoofish wrote:
| Hi. Thank you for your response. All of our work is
| transparent, if there is something you want to see or know,
| reach out on linked in or twitter. Other than that I think
| you are misrepresenting what is on the site, it says nothing
| of what you write
| mistermann wrote:
| The comments in this thread are such a fantastic
| demonstration of the dire need for tools and technology
| like this....and a good learning experience for the devs!!
| sdwr wrote:
| You built a platform to facilitate and track discussions,
| for people and AI.
|
| That's great, and maybe it's the future of harnessing AI,
| but it's not:
|
| - Conversational Game Theory
|
| - a dynamic equilibrium between computational, cognitive
| and psychological states
|
| - a public good that functions as an enhancement layer
|
| - immutable to subversion from bad faith actors
| hoofish wrote:
| Hi, thanks for your response. If you reach out to the founder
| on linked in, he is happy to give you a demonstration.
| hoofish wrote:
| There isn't any buzz words being used, you could simply look up
| with the words mean if you don't understand them.
|
| "Conversational" is plain english for conversation. "Game
| Theory" implies what it says.
|
| Which words made it so challenging? Let me know and I can
| explain.
| jsemrau wrote:
| Game Theory and Agent Reasoning?
___________________________________________________________________
(page generated 2024-11-28 23:02 UTC)