Towards a conversational agent that can chat about anything • Hacker News Board

Re: Towards a conversational agent that can chat about anything

#81

Post by rahimnathwani » Wed, Jan 29, 2020, 6:09 AM UTC

sriku wrote: post #74

darepublic wrote: post #47

Earlier quoted context omitted.

these nlp models are getting better and better but what we need ofc is for some model of the world to be constructed during the speech. If I tell you that yesterday I accidentally knocked a glass of water off the table and it fell on to soft carpet you could guess that it survived the fall without shattering. What we need is a chatbot that as you talk to it can update a 3d game/physics engine model from your words so…

Judea Pearl has been talking about this gap like forever now. According to him, causal modeling is the missing piece. I do believe it is a serious step up (i mean, does it take a model to look at 350GB of text to have that presented conversation?) .. however I don't know enough to know whether that is enough. (Reading TheBookOfNow and Causality in parallel)

I think you mean the book of why, not of now

Re: Towards a conversational agent that can chat about anything

#82

Post by rland » Wed, Jan 29, 2020, 6:40 AM UTC

grawprog wrote: post #61

andbberger wrote: post #59

Earlier quoted context omitted.

You definitely need a model of the world, but you probably don't want to be constructing it during speech. What you want is a generative model that you've trained on the simulation data ahead of time so you can quickly make inferences once deployed.

How would that make a conversation more lifelike? It'll still be a limited model of the world, unless somehow you intend to give it the entire breadth of human experience, and will still fall to the same shortcomings as every chatbot, ask it about something it doesn't know and it'll try and fit a response that gives it away as a bot, act confused in a way that gives it away as a bot or just say something nonsensical.…

Well, often times human beings miss metaphors, slang, and topical references, especially if they are speaking in another cultural group.

The gulf between even the most disparate human tribes is nothing compared to the gulf between an AI chat-bot and a human being.

I think it's entirely possible to make bots with simple models of the world. (Not that this is really a move any closer to that)

Re: Towards a conversational agent that can chat about anything

#83

Post by nradov » Wed, Jan 29, 2020, 6:45 AM UTC

Aperocky wrote: post #36

RugnirViking wrote: post #27

From the very first sample conversation they released: - Human: Hi! - Meena: Hey there! What's up? - Human: Same old, Monday blues...what are you up to? - Meena: I'm procrastinating on a paper I'm supposed to be writing. - Human: are you thinking of pulling an all nighter? - Meena: Possibly. What's your paper on? The bot has already mistaken facts about its own crafted persona and the human in less than 2 meaningful…

Haha, indeed. I think we're trying to stretch too far here. We've always dreamt of having a conversation with a bot without actually constructing the intelligence behind that bot. And it's not going to work. We should start with something simpler, like cats, which definitely have feeling, but have a mental capacity that is closer to what we may be able to emulate through software. And then monitor progress through it…

We should start with something simpler, like flatworms. We are far, far away from being able to accurately emulate a complex, social mammal like a cat. I doubt whether researchers can achieve cat equivalence in our lifetimes.

Re: Towards a conversational agent that can chat about anything

#84

Post by ai_ia » Wed, Jan 29, 2020, 6:56 AM UTC

darepublic wrote: post #47

RugnirViking wrote: post #27

From the very first sample conversation they released: - Human: Hi! - Meena: Hey there! What's up? - Human: Same old, Monday blues...what are you up to? - Meena: I'm procrastinating on a paper I'm supposed to be writing. - Human: are you thinking of pulling an all nighter? - Meena: Possibly. What's your paper on? The bot has already mistaken facts about its own crafted persona and the human in less than 2 meaningful…

these nlp models are getting better and better but what we need ofc is for some model of the world to be constructed during the speech. If I tell you that yesterday I accidentally knocked a glass of water off the table and it fell on to soft carpet you could guess that it survived the fall without shattering. What we need is a chatbot that as you talk to it can update a 3d game/physics engine model from your words so…

I second the approach, although not in terms of physics engine or world model but models that hold metadata about how an abstraction affect another one. When all the abstractions and their relationships could be mapped out or inferred, the models would start making better sense.

Re: Towards a conversational agent that can chat about anything

#85

Post by colorincorrect » Wed, Jan 29, 2020, 7:06 AM UTC

dnautics wrote: post #79

artfulhippo wrote: post #78

Earlier quoted context omitted.

This is a good test of capabilities, but not of humanity. A normal human response to such an order would be "f * off".

would it be better if it were prepended with "let's play a word game?"

maybe, but any regular human being might not want to play your stupid word game which isn't even fun at all asides for the AI researcher.

Re: Towards a conversational agent that can chat about anything

#86

Post by colorincorrect » Wed, Jan 29, 2020, 7:21 AM UTC

RugnirViking wrote: post #52

darepublic wrote: post #47

Earlier quoted context omitted.

these nlp models are getting better and better but what we need ofc is for some model of the world to be constructed during the speech. If I tell you that yesterday I accidentally knocked a glass of water off the table and it fell on to soft carpet you could guess that it survived the fall without shattering. What we need is a chatbot that as you talk to it can update a 3d game/physics engine model from your words so…

This might sound unrealistically complicated, and the approach suggested here certainly is, but the idea of simulating a world is a very important concept in our current models of human intelligence, with very small children spending a lot of their time learning basic concepts of cause and effect, properties of objects, materials and physics and so on. It reminds me of something I do in my current occupation, with a…

>very small children spending a lot of their time learning basic concepts of cause and effect, properties of objects, materials and physics and so on.

i do not believe that young children explicitly/consciously simulate in their minds to learn cause and effect and other things, though this might be up for debate

Re: Towards a conversational agent that can chat about anything

#87

Post by colorincorrect » Wed, Jan 29, 2020, 7:23 AM UTC

RugnirViking wrote: post #27

From the very first sample conversation they released: - Human: Hi! - Meena: Hey there! What's up? - Human: Same old, Monday blues...what are you up to? - Meena: I'm procrastinating on a paper I'm supposed to be writing. - Human: are you thinking of pulling an all nighter? - Meena: Possibly. What's your paper on? The bot has already mistaken facts about its own crafted persona and the human in less than 2 meaningful…

it is consistent for someone to procrastinate and work on something for a long time: you work for a long time while putting little effort. perhaps this was the intended interpretation?

Re: Towards a conversational agent that can chat about anything

#88

Post by probably_wrong » Wed, Jan 29, 2020, 7:33 AM UTC

colorincorrect wrote: post #87

RugnirViking wrote: post #27

From the very first sample conversation they released: - Human: Hi! - Meena: Hey there! What's up? - Human: Same old, Monday blues...what are you up to? - Meena: I'm procrastinating on a paper I'm supposed to be writing. - Human: are you thinking of pulling an all nighter? - Meena: Possibly. What's your paper on? The bot has already mistaken facts about its own crafted persona and the human in less than 2 meaningful…

it is consistent for someone to procrastinate and work on something for a long time: you work for a long time while putting little effort. perhaps this was the intended interpretation?

I think the problem is that "Meena" says she's writing a paper, but then immediately asks the human "what's your paper about?". The human is not writing any paper as far as we know.

Re: Towards a conversational agent that can chat about anything

#89

Post by allovernow » Wed, Jan 29, 2020, 7:36 AM UTC

In my experience, getting a bot to chat about bullshit is not a particularly useful pursuit in itself. There are far more useful ML paths to explore, like guided, interactive decisionmaking in a much more focused information field. And I think these naturally will lead to authentic conversation.

But to truly converse beyond an essentially overfit learned response domain requires real world knowledge(1) and learned relationships/heuristic simulation(2) in combination with decision making, and our nets aren't quite complex enough to get 1 and 2 represented sufficiently well (need lots more memory), while the decision making algorithm/architecture hasn't been developed yet...

But the pieces are all availably for assembly and industry is getting pretty close. If hardware continues to scale at a similar pace we can probably expect true AI in some form in the next hundred or so years. It won't initially be very human but if it is purposed (as it undoubtedly will be) to produce improved designs, by that point progress will effectively be exponential and probably impossible to predict.

All of this thanks I reluctantly admit to pioneering teams at places like Google and fb and Microsoft, and the open access nature of arxiv. I think, in proportion to its emerging complexity and value, machine learning may be one of the most quickly growing fields ever to exist. Humanity is quickly approaching a new era.

Re: Towards a conversational agent that can chat about anything

#90

Post by raducu » Wed, Jan 29, 2020, 7:38 AM UTC

colorincorrect wrote: post #87

RugnirViking wrote: post #27

From the very first sample conversation they released: - Human: Hi! - Meena: Hey there! What's up? - Human: Same old, Monday blues...what are you up to? - Meena: I'm procrastinating on a paper I'm supposed to be writing. - Human: are you thinking of pulling an all nighter? - Meena: Possibly. What's your paper on? The bot has already mistaken facts about its own crafted persona and the human in less than 2 meaningful…

it is consistent for someone to procrastinate and work on something for a long time: you work for a long time while putting little effort. perhaps this was the intended interpretation?

The issue is Meena is first saying it is working on a paper then asks the human what the paper is on; the human never mentioned he was working on any paper, Meena herself did, hence the inconsistency.