My new AI - made in an entirely new way, no other AI like this exists | Forum

#1

this is first model:

this is second model with smaller training data:

this is 3rd model, with huge training data and huge pattern groups:

3rd model is essentially huge. Its brain txt file is almost 500 megabytes.

Whats interesting is that it produced knowledge which isnt found anywhere in its training data. It combined "invisible hand self interest theory" to "debating", and as result, produced argument that appealing to self interest is an efficient debating strategy.

this AI doesnt use weights, and no it doesnt use markov chain either.

I used to play with markov chain, but it can never be good because it either produces incoherence or merely copies training data.

this AI tho, produces coherence without copying training data itself. It uses patterns from training data to form new sentences not found in training data itself.

And training time is extremely fast, it takes program about few seconds to make its fully ready "brain.txt" file it uses for chatting. It makes "brain.txt" file from training data.

this is the most advanced AI I have ever built. And the one which works surprisingly well, with very simple coding.

Edit comment

Mentions Text*

this is first model: <img src="https://debatecraft.s3.amazonaws.com/uploads/dea55aca-dc5f-4590-8ab8-c12dfb3d1c8b.png"> this is second model with smaller training data: <img src="https://debatecraft.s3.amazonaws.com/uploads/21336044-56c8-40cb-999c-de1b33ce1620.png"> this is 3rd model, with huge training data and huge pattern groups: <img src="https://debatecraft.s3.amazonaws.com/uploads/bcd05d97-055f-4293-9f4d-8c5b0d6e3b54.png"> 3rd model is essentially huge. Its brain txt file is almost 500 megabytes. Whats interesting is that it produced knowledge which isnt found anywhere in its training data. It combined "invisible hand self interest theory" to "debating", and as result, produced argument that appealing to self interest is an efficient debating strategy. this AI doesnt use weights, and no it doesnt use markov chain either. I used to play with markov chain, but it can never be good because it either produces incoherence or merely copies training data. this AI tho, produces coherence without copying training data itself. It uses patterns from training data to form new sentences not found in training data itself. And training time is extremely fast, it takes program about few seconds to make its fully ready "brain.txt" file it uses for chatting. It makes "brain.txt" file from training data. this is the most advanced AI I have ever built. And the one which works surprisingly well, with very simple coding.

#2

Did you even read the screens you posted?

Your AI output is mostly gibberish.

Maybe it's "made in an entirely new way", but there is a reason this way isn't used.

There's not much of a market for AI that speaks gibberish.

Edit post

Mentions Text*

#3

@SatanLucy

No other AI like this exists

The only rational statement made in your entire post.

Bot: I don't know enough information.

Brilliant. So, what does it know?

Bot: establishes a logical deduction argument for truth requires: truth requires: truth requires:

A fallacy is true in reasoning that is true in every possible interpretation...

You're kidding, right?

As a PhD in English Lit, my grade for this bot: F. An utter waste of cyberspace.

Edit post

Mentions Text*

We tell God what to do and then blame Him for our errors.

- Dr. Pet Dragon of Sorbonne University

#4

@fauxlaw, @Sidewalker

Your AI output is mostly gibberish.

Because it forms new sentences not found in training data, and of course not all of those sentences make sense.

Sure, I could make it merely repeat training data, and that would be 100% coherent, but then no creativity happens.

this is example of "coherent" bot:

So yeah, this one is "coherent", but problem in it is that it merely repeats from data. Produces nothing new. So it can never produce a single sentence not found in its training data.

Edit post

Mentions Text*

#5

the biggest issue for me isnt how to make chatbot coherent. that is easy, as shown in that coherent bot version.

the problem is, how to make chatbot form entirely new sentences while remaining coherent.

Repeating from training data and being coherent is easy. Using training data to make something entirely new not found in training data while keeping coherence? thats where real trouble starts for a simple chatbot. Its usually a dichotomy between coherence plus repetition or creativity plus incoherence.

Edit post

Mentions Text*

#6

@SatanLucy

Good luck monetizing the market for gibberish.

Edit post

Mentions Text*

#7

@Sidewalker

My AI is not for sale. At least not before I improve it a lot so it can be both coherent and creative, as opposed to being just one of those.

Edit post

Mentions Text*

#8

@SatanLucy

True creativity is not nonsense; it is not merely stringing words together whether or not they make sense. Any illiterate can do that, and that is definitively the king who wears no clothes just to demonstrate his fashion illiteracy, or the queen who wears transparent material, allegedly because she thinks her body is worthy to be revealed [they often are not]. Creativity is order; it is organizing chaos to make order. Therefore, the AI version serves no purpose.

Edit post

Mentions Text*

We tell God what to do and then blame Him for our errors.

- Dr. Pet Dragon of Sorbonne University

#9

@fauxlaw

Sadly, even in AI models, creativity comes from incoherence.

Its why temperature control in AI, lowering temperature results in AI which merely repeats training data. Increasing temperature means AI is more creative, but also more incoherent.

Edit post

Mentions Text*

#10

@SatanLucy

Sadly, even in AI models, creativity comes from incoherence.

What? From what was that one pulled? No, AI, itself, may be incoherent, and chaos is not creativity. Incoherence [chaos] is resolved by creativity, not the result of it. Don't be bass ackwards

Edit post

Mentions Text*

We tell God what to do and then blame Him for our errors.

- Dr. Pet Dragon of Sorbonne University

#11

@fauxlaw

Creativity usually demands something new, and reason why almost all successful ideas faced initial failure is because failure was result of creativity which later produced success.

tho my chatbot needs better design. I think I make a good blend of creativity and coherence by making it do two outputs.

Edit post

Mentions Text*

#12

@SatanLucy

Creativity usually demands something new, and reason why almost all successful ideas faced initial failure is because failure was result of creativity which later produced success.

Congratulations, you have successfully produced gibberish, and like you pointed out, nobody else is doing this, so you are the leader in the field of gibberish.

Maybe you can upgrade it to produce gobbledygook someday.

You should brand it, call it Jabbertwaddle maybe, or even better and more to the point, "The Nonsense Machine".

Edit post

Mentions Text*

#13

@Sidewalker

Sure

Edit post

Mentions Text*

#14

@SatanLucy

You are proof that AI can be used creatively.

Edit post

Mentions Text*

Conversation

Edit comment

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post

Edit post