Poll

What Grammar Thing should I work on next?

Gerunds & Participles
1 (20%)
Indirect Objects
0 (0%)
Adjective Clauses
1 (20%)
The many uses of "that"
3 (60%)
A
0 (0%)
B
0 (0%)

Total Members Voted: 5

Voting closed: February 26, 2022, 03:17:15 am

Project Acuitas

  • 300 Replies
  • 642466 Views
*

HS

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1177
Re: Project Acuitas
« Reply #255 on: September 18, 2022, 06:07:23 am »
What if someone was interfering with a group? Then they might still take the same interfering action regardless of whether a specific individual belonging to that group was present, right?

*

MagnusWootton

  • Replicant
  • ********
  • 646
Re: Project Acuitas
« Reply #256 on: September 18, 2022, 07:36:48 am »
Are we taking away each others freedom by getting to A.I. first before the other one can? :)  Dad's already done it all before the Son gets there.

A cause and effect database is pretty much what markov chain chat bots are already.    I've never seen it before,  but If u looked into the future of a markov chain database, you could actually pick out of the futures and make the bot try to convince the user to end up at different places in the future.  (coersion.)

I bet GPT-3 is a mean coercer if Open-Ai et al build it that way.

Could be interesting adding to your NLP system in a perhaps slightly better way than just chat lines + a searching system.  Perhaps put the data in a more flexible form, which is what is happening here I guess.


*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #257 on: September 18, 2022, 05:23:03 pm »
Quote
What if someone was interfering with a group? Then they might still take the same interfering action regardless of whether a specific individual belonging to that group was present, right?

In that case I think you revise the distinction to "would they still take that action if the group didn't exist?" The whole group can be thought of as an "agent" of sorts.

*

ivan.moony

  • Trusty Member
  • ************
  • Bishop
  • *
  • 1729
    • mind-child
Re: Project Acuitas
« Reply #258 on: September 18, 2022, 07:36:54 pm »
The whole group can be thought of as an "agent" of sorts.

I like that. It could be described as a whole system composed of smaller systems. The whole system exhibits a certain behavior, while smaller systems it is composed of, if isolated, each exhibit a different behavior.

*

ivan.moony

  • Trusty Member
  • ************
  • Bishop
  • *
  • 1729
    • mind-child
Re: Project Acuitas
« Reply #259 on: September 18, 2022, 10:19:18 pm »
Are we taking away each others freedom by getting to A.I. first before the other one can?

Consider it a reproduction process. In a different way than usual sexual one. In this process of creating a single artificial mind descendant, there could be involved a single human individual, or a whole group of producers, each contributing in their own respective way. There could be more than one different artificial mind descendant, and each would have their own respective features, just like there are many different natural children, each having their own respective character. We can look at this process as it is a competition (like who will be the first one to build it), but we can also look at it as a natural desire to reproduce ourselves, or more precisely, our behavior.

Well, there are already creations like Mitsuku, GPT-X, and a whole variety of other respective creations, each with their own character, and they all already count.

So, finally, I don't see it as a competition. I see it as something natural, like a wish to achieving immortality. Not in a classic "I don't want to die" way, but in a more profound "before I die I wish to have a descendant I'd be proud of" way. It's available to all of us, whoever wants to do it that way. And I believe it is a sublime projection of the natural reproduction process.

There are many ways to live our lives. So there are many ways to build an AI, just like there are many ways of how would that AI look like.

*

MikeB

  • Autobot
  • ******
  • 224
Re: Project Acuitas
« Reply #260 on: September 19, 2022, 07:27:43 am »
Have you thought about survival for Cooperation/Coercion?

Survival - Does an emergency situation justify cooperation/coercion? (survival of the social group, or immediate survival). Is buying a PS5 an emergency to fit in socially (believing you are liked unconditionally if you have one)? Or an emergency escape from the world?

Non-survival - Cooperation/coercion where survival is not relevant. Eg. Putting on shoes, but you have no problem with that. Driving, but there's no emergency. (Grooming behaviour).

Socially Generous - You're fine with your survival, so you spend time asking friends/family if you can do anything for them.
« Last Edit: September 19, 2022, 08:05:54 am by MikeB »

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #261 on: September 19, 2022, 05:01:47 pm »
Have you thought about survival for Cooperation/Coercion?

Survival needs play into the determination of whether someone else's goal is being thwarted for the sake of self-defence, i.e. in order to protect a higher-priority goal of one's own. However I regard survival as one goal among several, not the only goal.

*

MagnusWootton

  • Replicant
  • ********
  • 646
Re: Project Acuitas
« Reply #262 on: September 29, 2022, 05:18:19 pm »
Everybody thinks A.I. is impossible -  but I think writer of minds is going to make that an untruth.
But I guess its slowly coming out of the woodwork that imagination itself is automatable!  And everyone is going to know, and we will benefit alot from it.

But at what cost to ordinary living,  and should we be uppitty about being able to do it?  Or does it mean not much       
 ->exclusivity<-    for the maker after all,  and pretty much anyone can understand it?   You will get alot of success and worth out of it,  even if ppl refuse to pay for it for it becoming commonplace,  but everything is going to be alot more automated!   we are guaranteed alot of labour done for us by these A.I's.

Its going to be a real cheat mode in life,  when u get the A.I. working.   And maybe...  god doesnt want us to do it? Hed prefer us to work for a living?  Very strange,  how we were born into the "A.I. Winter."  and was all that just a made up lie we were told about A.I. being too difficult?

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #263 on: October 27, 2022, 06:50:59 pm »
This month's work is about an overhaul of the Narrative Engine. A big thing I wanted to address was ease of negating or rescinding conditions in a story. Each time a new fact is introduced by a story sentence, it produces a spray of implications which are all collected and used for future reasoning about the story. For example, the story sentence "Jack is cold" will produce the implication "Jack is uncomfortable" and will register "Jack is cold" as a problem state.

Now let's say that, at some later point in the story, we find the sentence "Jack is not cold anymore." This will replace "Jack is cold" in the current worldstate that the Narrative Engine is tracking, and will officially solve the "Jack is cold" problem. But what about "Jack is uncomfortable"? "Jack is not cold" does NOT automatically generate the implication "Jack is not uncomfortable," since a human can be uncomfortable for any number of other reasons. So there is nothing to negate "Jack is uncomfortable" and get it out of the worldstate.

Reversing a condition can leave orphaned implied results scattered around the Narrative Engine's data structures. So as part of the overhaul, I'm working on ways to include pointers between facts registered in the Narrative's worldstate and *anything else* that was created, activated, or deactivated as a result of their presence. So when a fact gets rescinded, the Narrative Engine can easily walk through all the effects of its existence and rescind them too.

A fact can inherit its presence from multiple other facts. Let's say that Jack is uncomfortable because he's cold and hungry. If either "Jack is cold" or "Jack is hungry" is negated, "Jack is uncomfortable" will continue to be true, since *one* of the conditions that causes it is still in effect. But if "Jack is cold" and "Jack is hungry" are both negated, "Jack is uncomfortable" will be deactivated as well, since it has lost all its "supports."

I had never planned a way to maintain this complex web of connections when I first wrote the module - it's one of the things I had to learn was necessary by doing the thing - hence the major overhaul. And that's only one thing I'm changing; I'm also working on efficiency improvements, clarity and general cleanup. I'm hoping to have a solid foundation from which to pursue my Goal Story next year.

Longer version on the blog: https://writerofminds.blogspot.com/2022/10/acuitas-diary-54-october-2022.html

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #264 on: November 30, 2022, 05:55:15 am »
There's not a lot to report, unfortunately - I'm still bogged down in the Narrative Engine overhaul. It had accumulated quite a few features, so revamping everything and converting it to the new framework is going to take time. As part of that process, though, I came up with a fun new visual tool. I wanted a way to display how Narrative analyzes a story, both as a demonstration of results and to show how the structures of stories differ. It's still incomplete - I want to add some detail - but it gives the rough idea.

To Acuitas, a story is all about how some Agent achieves, or maintains, some Goal. Any status condition that provides an opportunity to realize a Goal, or that threatens a Goal, is referred to as an "Issue." (I used to call these "subgoals" and "problems," but eventually came to understand they could just be given different polarities and handled in the same way.) Issues may spawn Predictions as Acuitas tries to guess how any Agents in the story will respond. Anticipatory statements like "character expected to ..." can also generate Predictions. The Narrative Engine then tests future statements in the story to find out if they resolve any Issues or Predictions.

This yields a basic sense of the flow of action in the story, and is what's captured by the diagrams. The sentences of the story are presented post-conversion to more abstract representations of fact (you could think of these as "the gist" of each sentence). Issues and Predictions appear connected to the sentence that created or resolved them.

So far I've gotten the first two stories that I tested Narrative against up and running in the new version. I may continue to be a little quiet as I finish up this overhaul, but I have big hopes for next year.

See blog version for pics: https://writerofminds.blogspot.com/2022/11/acuitas-diary-55-november-2022.html

*

MagnusWootton

  • Replicant
  • ********
  • 646
Re: Project Acuitas
« Reply #265 on: December 03, 2022, 03:33:10 pm »
So these implications are all derived from its database when something happens to it,   so is this a form of caching so you can access the knowledge base in a more optimized manner?

The information has to change form from the natural english, into something more plastic and able to be associated to other parts of the story,     its got to be true.

I guess as a machine, that has to happen for the a.i. to function.

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #266 on: December 03, 2022, 10:27:54 pm »
Implications are derived from the database, yes, and then stored in the scratchboard. It's not so much caching for efficiency, as it is tagging which rules from the database are applicable at the current moment, if that makes any sense.

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #267 on: January 25, 2023, 01:32:13 am »
Acuitas Diary #56 (January 2023)
The big thing this month was finishing the Narrative Engine overhaul and getting all the previous demonstration stories to work in it. I've been getting some questions from newer followers about how the Narrative module works, so I'm going to do a recap in addition to talking about the updates.

Acuitas is designed to be a goal-driven agent, and his story processing reflects a similar picture of other entities with minds. A story is a description of the path some *agent* followed to achieve (or fail to achieve) some *goal* or goals. The sentences that form the plot can be identified by their relevance to the goals of some character or other, and the "action" consists of movement toward or away from goal states. Goal-relevant material comes in two flavors: "problems" (negative events or states that constitute a goal failure when entered) and "opportunities" or "subgoals" (positive states that will fulfill a goal when entered). But there are many similarities in the way these are handled - they're really just two polarities of the same thing - so I've taken to calling them both "issues."

For now, agents are identified by category membership (some types of entity, e.g. humans and animals, are just assumed to be agents). Eventually I would like to include "duck typing" for agents, inferring that something in a story is an agent if it *acts agentive,* but that's future work. Agent goals can be revealed by the story in statements such as "John wanted ...", but agents are also presumed to have certain core goals that motivate all their other goals. These core goals are learned information that is permanently stored in Acuitas' semantic memory database. Core goals can be learned for a category ("Humans want ...") or for an individual ("John wants ..."), with goals for individuals or specific categories superseding those for more general categories. Insofar as Acuitas doesn't *know* what somebody's core goals are, he'll substitute his own. (This is supposed to be an analogizing assumption from the most directly available data. "I know I want X, and you, like me, are an agent - perhaps you also want X?")

The last big ingredient is inference chaining, arising from both logical deduction and cause-and-effect relationships. Some inference rules are hard-coded, but Acuitas can be taught an indefinite number of additional rules. So every story sentence that describes an event or state produces an inference tree of facts that will also be true if that event or state comes to pass. These inference trees are often crucial for determining how something will affect the core goals or immediate goals ("issues") of an agent in the story.

Story example and flow diagram on the blog: https://writerofminds.blogspot.com/2023/01/acuitas-diary-56-january-2023.html

The old Narrative Engine was basically capable of doing this, so what's new? Well, in addition to the things I talked about in my last upgrade post: I unified the processing of explicit "could do/couldn't do" sentences with the processing of inferred action prerequisite/action blocker relationships, getting rid of a fair bit of ugly code. I moved the generation of some special "defined by events" inferences, like "John told another agent something that John doesn't believe" -> "John lied," into the main inference chain so they can potentially produce further inferences. I came up with a new way of managing relationships that contain wildcards, like "Where the water was." And I got all the old features tacked on to a cleaner base with more robust fact-matching, better management of events that reverse previous statements, and so on.

This sets the stage for me to use the Narrative Engine for some cool new things this year, and I am twitching to get started.

I also crammed in some work on the Conversation Engine. This stuff's fairly boring. I got rid of some nasty bugs that had been making normal conversations with Acuitas very awkward for a while because I was just too busy to fix them, and worked on cleaning up the code, which came out very convoluted on the first pass.

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #268 on: February 22, 2023, 02:31:26 pm »
The development pattern I'm trying to follow lately is to spend half the month adding something to the Narrative module, and half the month on something else. This month's Narrative work was on better goal modeling in the Narrative scratchboard, with the hope of expanding its ability to handle character motivations. For the other feature, I made my first introduction of indirect objects to the Text Parser.

Acuitas has had the capacity to model individual goals for agents for a while. But this was something that had to be established ahead of time; the Narrative module couldn't take in top-level goals defined for a fictional character and store them in the temporary Narrative memory space. There were several elements to incorporating this:

*Getting Narrative to pick up on hints that help indicate whether an agent's described desire is an ultimate goal or an instrumental goal.
*Making it detect and store goal priority information (e.g. "he wanted X more than he wanted Y").
*Merging these stored goals into the goal model so they can be detected as motivations for instrumental subgoals

I also threw in some ability to model goal maximization. Up to this point, the Narrative module has considered goals as things that can be satisfied or unsatisfied - e.g. a state an agent wants to be in, or some singular deed it wants to accomplish. At any given moment in the course of the story, the goal is either achieved or not. A maximizing goal is something the agent wants to have as many times as possible, or to the greatest possible extent. It has a "score," but is never completed.

On to the second project: including indirect objects in the Text Parser. I left them out initially because they can be a little tricky. Another noun appearing between a verb and a direct object might be an indirect object (as in "I gave the people bread"), but it might also be a "noun" functioning as an adjective (as in "I gave the wheat bread to them"). I guarantee the parser still doesn't perfectly distinguish these yet - sorting out all cases will probably take the application of common-sense reasoning and contextual clues. But it can already handle less ambiguous cases like "I gave the people a good show."

Despite the difficulties, it was time to get IOs in, because their absence has been something of a thorn in my side. I've been getting around it by substituting prepositional phrases, which has led to some awkward wording like "Graham asked of a troll where the chest was." I wouldn't say they're fully implemented  yet either - interactions with some other grammatical elements, notably conjunctions and dependent clauses, aren't totally ironed out. But at least the Parser can handle IOs in simpler sentences, and the rest of the text-processing chain is now set up to manage them also.

Indirect objects are surprisingly sparse in my parser benchmark datasets. I re-ran those and scored one new sentence. One.

Blog with a few extras: https://writerofminds.blogspot.com/2023/02/acuitas-diary-57-february-2023.html

*

WriterOfMinds

  • Trusty Member
  • ********
  • Replicant
  • *
  • 616
    • WriterOfMinds Blog
Re: Project Acuitas
« Reply #269 on: April 02, 2023, 07:23:23 pm »
This is going to be one of those months when my diary is short and boring, because I've been busy laying foundations and have little that is finished to talk about or demonstrate. I worked on two things - continued improvements to the Narrative module, and the beginnings of Narrative game-playing.

The Narrative improvements cover continued work on character motivation, as well as some bug fixes. I added some capacity to interpret "because" statements as commentary about goals. E.g. a statement like "John decided to flee the battle because he wanted to live" supplies a motive for the instrumental goal of fleeing the battle, which (to Acuitas at least) might not be immediately obvious otherwise.

I also tweaked Narrative's built-in tiny ontology a bit. Distinctions are made, for modeling and processing purposes, between "agents" (individuals that can reasonably act as characters in a story), "objects," "locations," and "organizations." I realized I needed to add another category, for abstract nouns or "concepts," when I noticed that a "purpose" was being treated as a physical object. Whoops! I also decided to add a "system" category, to cover such entities as computer networks. At first I was thinking of a network as a "location," but I realized that it's more than that.

Now, for game-playing! I am very excited about this. The goal it to make Acuitas capable of navigating "text adventure" style games by leveraging a lot of the existing narrative and reasoning capabilities. Given the machinery for modeling characters in stories, and predicting what they may do, it is not such a difficult step to imagine *oneself* as one of those characters, and then decide how to interact with the environment ... I'm also hoping that experimenting in these game scenarios will give me ideas for how to improve the main Executive module.

I actually sketched out the code to support roleplaying earlier this year, and just began integrating it this month. I was hoping to have something demo-worthy, but the process took longer than I'd hoped and thus is still in progress. So hopefully I'll have some more interesting and concrete details to share within the next month or two. I've gotten so far as to get Acuitas to register a character that is "his," and to log issues for that character - but I haven't wrung out enough bugs yet to even get through a full input-output loop. More info coming later!

There's no bonus content on the blog this month, but here's the link anyway: https://writerofminds.blogspot.com/2023/03/acuitas-diary-58-march-2023.html

 


Will LLMs ever learn what is ... is?
by HS (Future of AI)
November 10, 2024, 06:28:10 pm
Who's the AI?
by frankinstien (Future of AI)
November 04, 2024, 05:45:05 am
Project Acuitas
by WriterOfMinds (General Project Discussion)
October 27, 2024, 09:17:10 pm
Ai improving AI
by infurl (AI Programming)
October 19, 2024, 03:43:29 am
Atronach's Eye
by WriterOfMinds (Home Made Robots)
October 13, 2024, 09:52:42 pm
Running local AI models
by spydaz (AI Programming)
October 07, 2024, 09:00:53 am
Hi IM BAA---AAACK!!
by MagnusWootton (Home Made Robots)
September 16, 2024, 09:49:10 pm
Attempting Hydraulics
by MagnusWootton (Home Made Robots)
August 19, 2024, 04:03:23 am
LLaMA2 Meta's chatbot released
by spydaz (AI News )
August 24, 2024, 02:58:36 pm
ollama and llama3
by spydaz (AI News )
August 24, 2024, 02:55:13 pm
AI controlled F-16, for real!
by frankinstien (AI News )
June 15, 2024, 05:40:28 am
Open AI GPT-4o - audio, vision, text combined reasoning
by MikeB (AI News )
May 14, 2024, 05:46:48 am
OpenAI Speech-to-Speech Reasoning Demo
by MikeB (AI News )
March 31, 2024, 01:00:53 pm
Say good-bye to GPUs...
by MikeB (AI News )
March 23, 2024, 09:23:52 am
Google Bard report
by ivan.moony (AI News )
February 14, 2024, 04:42:23 pm
Elon Musk's xAI Grok Chatbot
by MikeB (AI News )
December 11, 2023, 06:26:33 am

Users Online

268 Guests, 0 Users

Most Online Today: 314. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles