Category: Uncategorized
-
(Previous blog post on AI evals here: Validation Process with Agentic LLMs/Context Engineering) This post is about how to integrate expertise from Subject Matter Experts into AI systems. . Getting Started The essential directed workflow using an AI agent to get started is: Research –> Scenarios/Metrics (+ Modes) –> Master System Prompt You can direct…
-
Two different first-principle theories on what produces pink noise DOI: 10.13140/RG.2.2.26687.78246 . What is Pink Noise My interest in pink noise comes from a background in cognitive neuroscience: Pink noise shows up in the human brain — whether using electroencephalography (EEG), magnetoencephalograpy (MEG), or even in channel noise at the neuron cellular level. I haven’t…
-
How to think about the paradox of self-referential systems when thinking about cognition, language, engineered systems, and physics Self-referential paradoxes Mathematical proofs. I don’t want to spend too much time getting into the details of examples but perhaps you’ve heard of Godel’s incomplete theorem (& Tarski’s update to that), Tupper’s self-referential formula (just an equation…
-
How do Large Language Models integrate concepts/words/patterns? Existing theory assumes they store a large dictionary and do simple computation (linear addition) with concepts from that dictionary. I show multiple kinds of evidence that LLMs store (& use) complex integrations (non-linear relationships) between concepts/words/patterns, revealing this ability with a relatively simple mechanistic interpretability method — and…
-
[Reposted from April 2012 in response a inquiry about how multiresolution modelling could apply to human cognition] This is a condensed summary of modelling applied to brains/intelligent systems, that I wrote after reading a report on MRM. I’ve reposted here as a possible useful summary of intelligence/cognition. The report’s discussion was centered around how to…
-
why society, organizations, and our minds (and human-made intelligence agents) suffer from self-deception . I recently rewatched the Alan Turing biopic, Imitation Games, which ends with Alan Turing’s team not only cracking the German Enigma code, but hiding their discovery from their own military branches and government. The logic is argued as follows: If the…
-
November 17, 2025 In this post, I’m going cover how I went from being unaware that a field existed (Mechanistic Interpretability, AI Alignment), to getting a full research paper accepted at a conference with a reported acceptance rate of 17% (AAAI 2026), in only four weekends. Readers may ask: Now keep in mind, I was…
-
Industry defectors are becoming increasingly loud that LLMs are not the path forward to human intelligence. What structure in current AI is missing from a human intelligence point of view? In the last couple weeks, a couple prominent AI researchers have voiced their disbelief that LLMs are not the path forward to human-level AI and…
-
The primary objectors of the idea that we have permanent limitations of comprehension of the universe and ourselves include the misinformed or confused who seem to be betting short on humanity. They do this by using a honed skillset to obscure and create wonder (that maybe an unintentionally evolved skillset by them, but one that…
-
As discussed previously, our intelligence relies on feature extraction and abstraction. This is also true of our language or any of our systems of representation or understanding. We break down the real world into features and categories. This works within scopes. We do this with language, at the detailed and abstract resolutions. We also do…
Omar Claflin 