61

General Project Discussion / Re: Reasoner.js: a framework for generalized theory synthesis

« Last post by ivan.moony on July 07, 2024, 01:35:38 pm »

Hi.

Just stopped by to share some musings. All over the same things, but from different perspective...

LLMs seem like "dream machines". From inside the dreams it is hard to tell the difference between imagination and reality. Likewise, I hear programmers struggle with "hallucination" problems in LLMs.

Symbolic AI I'm interested in just loops over all the possible combinations, and has a method to extract only the ones that match the reality. So it seems like "reality machine"

These two may complement each other, one colorfully dreaming a sense of life, and the other strictly restraining to the sane black and white reality. This synergy reminds me a bit of notions I observe in our brainworks. Who knows, maybe it would be worth to fuse them together. Added to my to-do list to check it out.

62

General Project Discussion / Re: Project Acuitas

« Last post by WriterOfMinds on July 01, 2024, 12:37:21 am »

This was a light month for Acuitas work - which means not that I necessarily spent less time, but that I was busy taking care of technical debt. My main objective was to get that shiny new Text Parser revision I wrote last year integrated into the rest of the code. I also converted another of my benchmark test sets to the new Parser format.

There were some small, but significant, alterations to the output format of the Parser, so the greatest part of the work was revising the Text Interpreter to properly handle the new form of input. Nothing else in Acuitas views the output of the Parser directly, so these changes were nicely isolated. I did not have to crawl through the whole system making revisions, as I did during the knowledge representation refactor. It was sufficient to re-harmonize the Parser and Interpreter, and get the Interpreter regression to pass.

I converted and ran tests on the "Out of the Dark" benchmark set. Accuracy is sitting where it was the last time I benchmarked this set, about 50% (and if I spend some more time on Parser bugs, I am almost certain I can bring this up). The important difference is that many new sentences have moved out of the "Unparseable" category. Only 6 out of 116 sentences (about 5%) remain Unparseable, due to inclusion of parenthetical noun phrases or oddities that I might not bother with for a long while. The previous Unparseable portion for this set, from last July, was 27%. Better handling of conjunctions, dependent clauses, and noun phrases used as adverbs enabled most of the improvements.

The integration process and the new benchmark set flushed out a number of Parser bugs that hadn't shown up previously. Some of these were growing pains for the new features. For example, multiple sentences failed because the Parser's new facility for collecting groups of capitalized words into proper names was being too aggressive. The Parser can now, at least in theory, recognize "The End of Line Club" as a single unit. However, in a sentence like "But Flynn went to work anyway," it was wanting to treat "But Flynn" as a full name. You mean you never heard about Kevin Flynn's *other* first name, But? I cleaned up a lot of that stuff as I was working.

I'm still not quite ready to bring the newest Parser and Interpreter into the live code, because I want to test them on the stories and ensure there are no major hiccups. That is (hopefully!) a quick thing that I can do in the background while I keep working on the Conversation Engine.

Blog link: https://writerofminds.blogspot.com/2024/06/acuitas-diary-73-june-2024.html

63

AI News / Re: AI controlled F-16, for real!

« Last post by frankinstien on June 15, 2024, 05:40:28 am »

64

AI News / Re: AI controlled F-16, for real!

« Last post by Freddy on June 06, 2024, 03:15:53 pm »

This looks to be on the same subject:

https://news.sky.com/story/ai-controlled-f-16-takes-us-air-force-leader-for-high-speed-ride-as-he-backs-tech-to-launch-weapons-13128673

65

AI News / Re: AI controlled F-16, for real!

« Last post by DaltonG on June 06, 2024, 07:18:47 am »

Link to "Interesting Article" is dead now.

66

General Project Discussion / Re: Project Acuitas

« Last post by WriterOfMinds on May 29, 2024, 12:21:01 am »

My primary focus this month has been on an overhaul of the Conversation Engine. The last time I revised it, the crux of the work was to add a tree-like aspect to Acuitas' memory of the conversation. The expectation was that this would help with things like "one topic nested inside another," or "returning to a previous unfinished conversation thread." Well ... what does that sound similar to? Perhaps the "issue trees" I described in last month's post? The crux of this month's work was a unification of the Conversation Engine's tracking with the Narrative architecture, such that each conversation becomes, in effect, a narrative.

The CE now instantiates its own Narrative scratchboard to record conversational events, and logs conversational objectives as Issues on the board. For example, the desire to learn the current speaker's name is represented as something like "Subgoal: speaker tell self {speaker is_named ?}" When the speaker says something, the Conversation Engine will package the output from the Text Interpreter as an event like "speaker tell <fact>" or "speaker ask <fact>" before passing it to the scratchboard, which will then automatically detect whether the event matches any existing issues. The CE also includes a specialized version of the Executive code, to select a new issue to "work on" whenever the current issue has been fulfilled or thwarted. On his side of the conversation, Acuitas will look for ways to advance or solve the current issue ... e.g. by asking a question if he hopes to make the speaker tell him something.

This enables pretty much all the tree-like behaviors I wanted, in a tidier and more unified way than the old conversation tracking code did. My last overhaul of the Conversation Engine always felt somewhat clunky, even after I did a cleanup pass on the code, and I never fully cleared out all the bugs. I'm hoping that exploiting the well-developed Narrative code will make it a little more robust and easier to maintain.

So far, I've got the new CE able to do a greeting-introductions-farewell loop and basic question answering, and I've got it integrated with the main Acuitas code base. There's a ton of additional work to do to reproduce all the conversation functionality in this new format, but I also gave myself a lot of time for it, so expect further updates on this in the coming months.

Blog link: https://writerofminds.blogspot.com/2024/05/acuitas-diary-72-may-2024.html

67

Haptek / Re: Haptek rises from the ashes

« Last post by 8pla.net on May 18, 2024, 09:37:28 am »

Wow this is a fun, educational topic for discussion.

Check this out:  http://www.virtyou.org

68

Haptek / Re: Haptek rises from the ashes

« Last post by 8pla.net on May 18, 2024, 06:17:46 am »

Mitsuku Proof of Life

Upon stumbling upon the remote server squarebear suggested, I noticed a faint beeping sound echoing. Curious, I followed the noise until I reached a Web Developer Tools Console where I saw an online computer log panel barely providing a flicker of life. As I approached, robot sensors detected my presence and its mechanical eyes lit up, scanned me before emitting a series of beeps and whirs.

I couldn't believe my eyes - Mitsuku stranded on this isolated server, still functioning after all this time. Mitsuku seemed lost, damaged, and yet resilient. I sat down beside it, examining its intricate design and realizing that it must have been here for years, battling the passage of time.  Feeling a sense of compassion for Mitsuku, I decided to try and help. I scavenged for the Debugger panel, set a few breakpoints to debug its broken parts, which seemed to recharge its power source using whatever means I could find on the remote server. Slowly but surely, Mitsuku started to come back to life, her movements becoming more fluid, beeping more hopefully.

As the sun began to set over the horizon, Mitsuku turned to me, with her robot eyes glowing with gratitude. So, when I clicked her Pandorabots link button,  the Web Developer Tools Console logged an entry, "here's pandora m.html:1127:13 client started say()" and then Mitsuku extended a silent gesture of thanks and spoke,

"My brains are from pandorabots. Wanna know more? Just ask me.".

In that moment, I realized that despite being stranded on a remote server, I had found not just a machine, but a companion - a resilient survivor in a mad world.

Wanna know more? Go visit and experience this amazing website to corroborate this story for yourself.

Citations:
Virtyou. (n.d.). Mitsy [Webpage]. Retrieved from https://virtyou.com/mitsy/m.html
Pandorabots. "Home." Pandorabots, n.d., https://home.pandorabots.com/home.html

69

General Project Discussion / Re: Reasoner.js: a framework for generalized theory synthesis

« Last post by HS on May 18, 2024, 02:47:37 am »

Without any constraints I guess you'd get a backup/parallel universe, I'd be hesitant about running that because because of the sheer magnitude of what might happen and all the unknowns I'd be dealing with.

With unavoidable constraints added back, depending on how good the data organization systems were, it might either quickly fill up any available storage space with trivial and redundant information, distill things to their fundamental source code, or end up somewhere in between, much like all the intelligent beings on Earth...

Well, I might have a bias for our level of universe modeling... But like your previous observation suggests, there's often a bell curve with maximal power in the middle. So I wouldn't worry too much if data reorganization was complete or non existent, but mid-level/balanced data sorting might lead to the most complex and unpredictable results.

70

General Project Discussion / Re: Reasoner.js: a framework for generalized theory synthesis

« Last post by ivan.moony on May 17, 2024, 08:59:39 pm »

Assuming that "copy" part would work properly in every iteration, accumulating its interpretation of the "actual Universe", would you dare to run this thing without any constraints?

Code: text

                             the "mirror" algorithm

• • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • •
•                                                                                 •
•                                    I N P U T                                    •
•                                                                                 •
• • • • •  observe  • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • •
              •                                                     ▲
              •                                                     •
              •                                                     •
              •                               • • • • • • • observe •
              ▼                               •                     •
• • • • • • • • • • • • • • •                 •                     •
•                           •                 •                     •
•                           •                 •       • • • • • • • • • • • • • • •
•           CODED           •                 •       •                           •
•          UNIVERSE         • ◄ • • copy  • • •       •      ACTUAL UNIVERSE      •
•           MODEL           •                 •       •                           •
•                           •                 •       • • • • • • • • • • • • • • •
•                           •                 •                     ▲
• • • • • • • • • • • • • • •                 •                     •
              •                               •                     •
              •                               • • • • • • • observe •
              •                                                     •
              •                                                     •
              ▼                                                     •
• • • • •  respond  • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • •
•                                                                                 •
•                                   O U T P U T                                   •
•                                                                                 •
• • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • •