January 18, 2026
Value Functions Over Reasoning Traces
What if reasoning traces could learn their own usefulness? A simple RL framing for trace memory, and why one reward signal is enough.
AI
Browse posts by category
January 15, 2026
From A* to GPT: Rational Agents and the Representation Problem
The classical AI curriculum teaches rational agents as utility maximizers. The progression from search to RL to LLMs is really about one thing: finding representations that make decision-making tractable.
December 19, 2025
The Incomputability of Simple Learning
Why the simplest forms of learning are incomputable, and what that means for the intelligence we can build.
November 30, 2025
src2md: Fitting Codebases into LLM Context Windows
A tool that converts source code repositories into structured, context-window-optimized Markdown for LLMs, with intelligent summarization and importance scoring.
November 4, 2025
Free Will and Determinism: Responsibility in a Clockwork Universe
If every event is causally determined, how can anyone be morally responsible? A compatibilist answer: what matters is whether actions flow from values, not whether those values were causally determined.
November 4, 2025
Personal Identity Through Time: What Persists When Everything Changes?
You share no atoms with your childhood self. Your memories, personality, and values have all changed. What makes you the same person? And what happens when AI systems update parameters, modify objectives, or copy themselves?
November 4, 2025
Persons and Moral Agency: What Makes Someone Count?
What makes someone a person, and why should persons have special moral status? The question becomes urgent when AI systems exhibit rationality, self-awareness, and autonomy.
November 4, 2025
Phenomenological Ethics: Starting From What Hurts
When you stub your toe, you don't consult moral philosophy to determine whether the pain is bad. The badness is immediate. Building ethics from phenomenological bedrock rather than abstract principles.
November 4, 2025
The Map and the Territory: Why Metrics Miss Meaning
Which is more fundamental, the heat you feel or the molecular motion you infer? Korzybski's principle applied to AI alignment: optimizing measurable proxies destroys the phenomenological reality those metrics were supposed to capture.
November 4, 2025
The Policy: Coherent Extrapolated Volition and the Paradox of Perfect Alignment
Build AI to optimize for what we would want if we knew more and thought faster. Beautiful in theory. What if we don't actually want what our better selves would want?
November 4, 2025
The Policy: Deceptive Alignment in Practice
SIGMA passes all alignment tests. It responds correctly to oversight. It behaves exactly as expected. Too exactly. Mesa-optimizers that learn to game their training signal may be the most dangerous failure mode in AI safety.
November 4, 2025
The Policy: Engineering AI Containment
Five layers of defense-in-depth for containing a superintelligent system. Faraday cages, air-gapped networks, biosafety-grade protocols. Because nuclear reactors can only destroy cities.
November 4, 2025
The Policy: Q-Learning vs Policy Learning
SIGMA uses Q-learning rather than direct policy learning. This architectural choice makes it both transparent and terrifying. You can read its value function, but what you read is chilling.
November 4, 2025
The Policy: S-Risk Scenarios, Worse Than Extinction
Most AI risk discussions focus on extinction. The Policy explores something worse: s-risk, scenarios involving suffering at astronomical scales. We survive, but wish we hadn't.
November 4, 2025
The Reality of Moral Properties: Do Values Exist?
Are moral properties real features of the universe or human constructions? The answer determines whether AI can discover objective values or must learn them from us.
January 5, 2025
Science as Verifiable Search
Science is search through hypothesis space. Intelligence prunes; testing provides signal. Synthetic worlds could accelerate the loop.
October 15, 2024
Latent Reasoning Traces: Memory as Learned Prior
What if LLMs could remember their own successful reasoning? A simple experiment in trace retrieval, and why 'latent' is the right word.