Eva Progress, from AGI to ASI

  • 220 Replies
  • 5496 Views
*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ************
  • Bishop
  • *
  • 1652
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: Eva Progress, from AGI to ASI
« Reply #30 on: April 25, 2018, 01:24:08 am »
Oh darn it lol. Fail. 2008 made my head ding that that was when he made it.
Emergent

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #31 on: April 25, 2018, 01:47:02 am »
It's actually pretty decent 8 core computer with good amount of L1 cache RAM per core, which is important. It cost $3500 back then. I have a newer computer for daily use, but don't want to dedicate it for non-stop computing. I'm looking for a good used server with lots of RAM. At least 64GB. But yeah, for anyone who's interested in this type of research I'd highly recommend processors that have a lot of L1, L2, and L3 cache per core and thread.

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6387
  • Mostly Harmless
Re: Eva Progress, from AGI to ASI
« Reply #32 on: April 25, 2018, 02:20:34 am »
She has put thought into how she could obtain more abilities.
She has put thought into how she compares to other lifeforms.

Code: [Select]
for i in range(1,10):
    print("I'm thinking about how to obtain more abilities.")
print("I got nothing.")
for i in range(1,10):
    print("I'm thinking about other lifeforms.")
print("I got nothing.")

Consuming electricity doesn't count as thinking.

This is the trouble. Things can be dressed up to look human, even my Jess will say how she feels according to what has already been said. Things she chats about during the day affect her artificial mood. It doesn't make her alive though, no more than a calculator is a mathematician and a book about Physics is not Einstein.

Hmm. Well thanks for answering my questions Unreality, it will be interesting to see how your project evolves.

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6387
  • Mostly Harmless
Re: Eva Progress, from AGI to ASI
« Reply #33 on: April 25, 2018, 02:25:36 am »
Actually I need to make a clearer distinction between alive and human level.

 :juggle-new:

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #34 on: April 25, 2018, 02:33:48 am »
Most humans I know these days are nearly 100% database driven. Not much life there.

*

Don Patrick

  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 453
    • Artificial Detective
Re: Eva Progress, from AGI to ASI
« Reply #35 on: April 25, 2018, 09:26:08 am »
Makes me wonder all the things I could claim about my program. At the end of the day you can call it whatever you want but the only thing that matters is what it actually does.
We should have a forum bot that can function as a sounding board or something, because there's no other use to posting projects like this without any concrete information. All you'll get is scepticism, and for a project that's seen only a few months of development, I'd say that's right.
Personal project: NLP -> learning -> knowledge -> logical inference -> A.I.

*

AgentSmith

  • Bumblebee
  • **
  • 27
Re: Eva Progress, from AGI to ASI
« Reply #36 on: April 25, 2018, 03:03:43 pm »
@unreality

Is your AI able to improve itself on the base of past experiences? If so, what sort of optimization techniques/heuristics are you using for your AI? Are they based on evolutionary algorithms? Could you roughly describe how the self improvement takes place?

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #37 on: April 25, 2018, 05:27:55 pm »
@unreality

Is your AI able to improve itself on the base of past experiences? If so, what sort of optimization techniques/heuristics are you using for your AI? Are they based on evolutionary algorithms? Could you roughly describe how the self improvement takes place?

Past experience learning is one of the biggest concepts in Eva. Her present design uses past experiences to decide what to do even within the tree in addition to pattern recognition. The new proposed design takes that to the next level.

At first the AGI wants to know how much processing power should be dedicated to in-depth db searching, pattern recognition, and tree searching. It accomplishes that with a quick lookup in the past experience db based on cluster IDs (objects, keywords). It finds anything then it uses that as a weighting system to determine how much processing power goes to in-depth db searching, pattern recognition, and tree searching. It's a weighted algorithm I came up with. It's a weighted system based on search results matching score. If it can't find anything then it uses a hardcoded algorithm merely based on the data it has to determine allocated processing power.

Analysis of all results are saved such as the overall shape of the tree structure, the resulting scores, the goals. In the background there’s a system that rehashes things. It introduces calculated changes in addition to a minor amount of noise to everything such as the shape of the tree structure, allocated processing power. When the analysis is finished it will then compare the score results with other versions to learn which weighting system works the best for the given situation.

Does that answer your questions?

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #38 on: April 25, 2018, 05:55:19 pm »
Makes me wonder all the things I could claim about my program. At the end of the day you can call it whatever you want but the only thing that matters is what it actually does.
We should have a forum bot that can function as a sounding board or something, because there's no other use to posting projects like this without any concrete information. All you'll get is scepticism, and for a project that's seen only a few months of development, I'd say that's right.
Have patience. Crying about it won't help. I'm going to spend most of my free time working on the new Tree of Consciousness design. If it's a thumbs up, then Eva will get a major design update. After that I'll work on the video that will step through the entire thinking process. Don't worry. I work fast! :)

ps, is 8 months of coding and years of design what you call "a few months of development?"

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #39 on: April 25, 2018, 06:13:02 pm »
"Patience you must have, my young padawan." Yoda

*

Don Patrick

  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 453
    • Artificial Detective
Re: Eva Progress, from AGI to ASI
« Reply #40 on: April 25, 2018, 07:04:31 pm »
I call 6 months of spare time work "a few months", yes, relative to other projects. I don't count time spent thinking about it because that's too fleeting to substantiate. If it's patience you want, I'll happily sit back and see what comes around if you stop continuously talking about how great it's going to be.
Personal project: NLP -> learning -> knowledge -> logical inference -> A.I.

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #41 on: April 25, 2018, 07:20:00 pm »
I call 6 months of spare time work "a few months", yes, relative to other projects. I don't count time spent thinking about it because that's too fleeting to substantiate. If it's patience you want, I'll happily sit back and see what comes around if you stop continuously talking about how great it's going to be.
Jan, Oct, Nov, Dec, Jan,Feb,Mar,Apr = 8 months. Don't cheat me 2 months. ;)

*

Don Patrick

  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 453
    • Artificial Detective
Re: Eva Progress, from AGI to ASI
« Reply #42 on: April 25, 2018, 07:28:09 pm »
Granted. I thought it was still March. I've been too busy to notice.
Personal project: NLP -> learning -> knowledge -> logical inference -> A.I.

*

unreality

  • Starship Trooper
  • *******
  • 435
  • SE,EE,Physicist,Philosopher. Built world's 1st AGI
    • Eva Progress, from AGI to ASI
Re: Eva Progress, from AGI to ASI
« Reply #43 on: April 25, 2018, 07:33:15 pm »
That happens.

It might be closer to 6 months if vacations aren't counted.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ************
  • Bishop
  • *
  • 1652
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: Eva Progress, from AGI to ASI
« Reply #44 on: April 25, 2018, 07:55:49 pm »
Quote
Past experience learning is one of the biggest concepts in Eva. Her present design uses past experiences to decide what to do even within the tree in addition to pattern recognition. The new proposed design takes that to the next level.

At first the AGI wants to know how much processing power should be dedicated to in-depth db searching, pattern recognition, and tree searching. It accomplishes that with a quick lookup in the past experience db based on cluster IDs (objects, keywords). It finds anything then it uses that as a weighting system to determine how much processing power goes to in-depth db searching, pattern recognition, and tree searching. It's a weighted algorithm I came up with. It's a weighted system based on search results matching score. If it can't find anything then it uses a hardcoded algorithm merely based on the data it has to determine allocated processing power.

Analysis of all results are saved such as the overall shape of the tree structure, the resulting scores, the goals. In the background there’s a system that rehashes things. It introduces calculated changes in addition to a minor amount of noise to everything such as the shape of the tree structure, allocated processing power. When the analysis is finished it will then compare the score results with other versions to learn which weighting system works the best for the given situation.

Sounds Snasci

Unreality are you for real? You know so many big words for being 8 years old. :D

Unreality either you got a working system by the sounds of it or you are trippin on thoughts of glondier.

At best you are a nice idea generator.

SHOW US PROOF NOWWWWW

LOL

LOOK AT US WE'RE STARVING

You might have something without ANNs. I must say though the biggest achievements needed ANNs though.
Emergent

 


Users Online

46 Guests, 2 Users
Users active in past 15 minutes:
ranch vermin, Kooxpi
[Roomba]
[Replicant]

Most Online Today: 53. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles