My post on AGI type approaches based on brain vs LLMs

 I asked this into Chat GPT (source chatgpt question)

"So when you look at current AI technology like LLM technology, it is currently, it is highly based on digital prompt inputs and analyzing large datasets with billions of parameters from text data.   The human brain does not necessarily operate that way.   What are current approaches to bridge the gap between low tech human brain processes to the machine learning algorithms with LLMs.  Projects like the numenta project and thousand brain project"

Here is the response from chatgpt - source chatgpt model as of Jun5.


"Recent AI research increasingly looks to the brain for inspiration. Neuroscience-derived ideas—such as sensorimotor learning, modular cortical columns, and memory consolidation—are being used to overcome limitations of today’s deep learning systems. For example, Numenta’s new Thousand Brains Project is an open-source initiative to build AI on cortical principles (sensorimotor input, grid-cell reference frames, parallel “columns”, and continual learning)numenta.comarxiv.org. Numenta describes its framework as “open-source sensorimotor learning… based on the principles of the neocortex”numenta.com. In this view, intelligent agents learn by moving and sensing in the world, building many partial object models in parallel and “voting” to form coherent perceptions"

"

Numenta’s NuPIC: Brain-Based LLM Inference

In parallel, Numenta applies its neuro-inspired algorithms to enhance large language model (LLM) deployment. Their product NuPIC (Numenta Platform for Intelligent Computing) is a commercial inference engine that “draws on Numenta’s decades of neuroscience research” to run LLMs efficiently on CPUsintel.comventurebeat.com. NuPIC uses novel data structures and memory-optimized routines derived from cortical theory. VentureBeat reports that NuPIC can improve efficiency by up to 100× on some workloads and dramatically cut inference cost, enabling LLMs to run on commodity hardware"

"In summary, a diverse array of initiatives is actively fusing neurobiology and AI. Companies like Numenta and Inait explicitly apply brain principles (cortical columns, causal learning, continuous memory) to AI systems, while startups like Cortical Labs and BrainChip implement biological or spike-driven hardware. New research (e.g. Larimar, BriLLM, CTM) embeds cognitive concepts (episodic memory, signal timing) into LLMs and neural nets."

Also:

1. Static vs. Continuous Learning

LLM flaw: LLMs are trained on a fixed dataset and do not learn after deployment unless fine-tuned with expensive retraining. They can’t adapt in real time.

Brain advantage: The human brain learns continuously from experience. It can adapt moment-by-moment, retain or forget information flexibly, and generalize from limited data.

2. Lack of Embodiment

LLM flaw: LLMs are text-only, disembodied systems. They do not interact with the physical world or receive real sensorimotor feedback.

Brain advantage: Brains are embedded in bodies. Humans learn by interacting with and sensing the world—touch, movement, vision, hearing, smell, etc. This grounded learning leads to richer, more flexible understanding.

On distributed AI

. Autonomous Agents + Blockchain (Smart Contracts)

  • Concept: AI agents run autonomously, interact with smart contracts on-chain, and use the blockchain for identity, data integrity, and incentives.

  • Key Features:

    • AI logic off-chain (e.g., in Python/LLMs) but interacts with on-chain components.

    • Payments, access control, and decision logs are recorded on-chain.

  • Examples:

    • Fetch.AI – Decentralized agents for Web3 and IoT that interact via a multi-agent framework using machine learning and blockchain.

    • Ocean Protocol – Decentralized data exchange with AI/ML model sharing, where agents can request and pay for data or predictions.

    • SingularityNET – Marketplace for decentralized AI services, where agents and services can interact via smart contracts and APIs.

Comments

Post a Comment

Popular posts from this blog

JVM Notebook: Basic Clojure, Java and JVM Language performance

Image
"Measure, don't guess. The primary goal of all performance tuning exercises should be maximize the end user experience given the resource constraints." [1] "It isn't so much a "farewell to the J" as an expansion of the platform opportunities Java provides. Sun's investment to power ongoing development of JRuby and Jython broadens the range and reach of Java, as a whole." -- Rick Ross Overview and JVM Languages    One of the exciting trends to recently emerge from the Java community is the concept of the JVM language. These technologies are all that you would expect them to be. They are implementations of languages that run on the Java Virtual Machine. Some are newly created and some are based on existing, more mature languages. JRuby, Jython are two JVM languages based on CRuby and CPython. Groovy, Scala, Clojure are three completely new JVM languages that were created to add new language features that weren't supported by the core Ja...
Read more

On Unit Testing, Java TDD for developers to write

It has been a while, let's kick off 2017 with a blog entry. I have read and I am reading about four or five posts a day about unit testing. It really has been a long time obsession for me. I have moved past the technical and practical considerations on unit testing frameworks and done with the debates with "should you use Junit or Mockito or Karma?" I am more interested in the psychology of unit testing, who does it, likes it, hates it? It really is one of those easy to learn, hard to master concepts. For example, many many may play chess when they are young and can end up being horribly chess players most of their life, I am part of that majority. Unfortunately, I have never played chess and sat down for hours and tried to master it. I never see the common patterns or have a developed end game. I mostly just play with a knowledge of the basic rules. Following good unit testing practices within your software development shop is a lot like playing chess. It is easy to le...
Read more

Is Java the new COBOL? Yes. What does that mean, exactly? (Part 1)

Image
"If you want to know the past, look at your present. If you want to know the future, look at your present." -- Gautama Buddha Java is the new COBOL, whaaaat?     If you are software developer that mainly writes applications for the web; even if you aren't a Java/J2EE developer, you have probably heard the new meme circulating the web and blogosphere. "Java is the new COBOL" . Most blogs and technical writers regurgitate that statement and follow-up by saying that EJBs suck, and some companies are considering Ruby on Rails. I didn't really think much of these posts. I get the impression that a lot of these "managers" don't write any Java or COBOL code. They are really not highlighting the seriousness of the problem. COBOL development has remained stagnant for decades. Java may see the same problem in the future. The Pentagon/DOD has a trillion dollar COBOL problem because it is so difficult to change their ancient infrastructure. Anyon...
Read more