Hacker News Reader

Comment by darepublic | Hacker News Reader

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 that common sense implications of your statements can be gleaned. As you speak it will simulate what you are describing and then use info gathered from the simulation to draw conclusions.

View on HN

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 robot. It makes predictions about how a certain motor movement will result in a change in position, then measures progress in the real world. Should the prediction and reality diverge significantly (more than a particular amount), it stops and calls a human to look into what happened. I can imagine AI techniques using this kind of thing to guess what will happen next in a series of events, with the result's divergance from the guess weighting the learning rather than a steadily decreasing weight. Perhaps this is already a thing though, I'm no AI researcher

>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

Who said anything about "consciously"? It doesn't need to be conscious to affect the conversation.

as to whether it is conscious or not influences whether you would want to model it a-la 3d physics engine, or if not then perhaps there is a more elegant solution we do not know of yet

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.

There's things like metaphors, slang, topical references, all things that end up in conversations that change regularly in their meaning and usage. Then there's the unspoken parts of conversations. The implications behind different wordings, ways of writing things, words left unsaid, sarcasm, tone(even in text tone is conveyed in some form).

Humans do all these things while conversing almost subconsciously, each individual person does these things and comprehends these things uniquely based on years and years of sensory input and model building from a huge variety of sources, in a way that's individually unique and poorly understood. How would you even begin to train a model to even a remote semblance of that?

You don't even have to trick it with slang. Maybe I am behind but so far I have never seen a bot that can consistently or even most of the time understand context. They seem to all seriously struggle with anything more than a random sentence that was determined a probable result of the last message the user sent.

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)

Kind of an open problem on how to make a generative model which is sufficiently powerful :)

But that is basically what humans do - we don't run internal simulations, we have a model we've trained over a lifetime of experiences with the world that judges the likelihood of a given scenario

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

Correct. Thanks and sorry about the typo. Too late to edit it, looks like.

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.

GPT-2 showed us that simply having a huge parameter space can be enough for internal consistency. Have you read the unicorn valley article it generated?

The output was cherry picked.

This

Reply on news.ycombinator.com