Stack Overflow for Ethics: Governing AI with Feedback, Not Faith
A control-theoretic reading of the Social Responsibility Stack, and why responsible AI needs monitors, thresholds, rollback paths, and governance authority—not just principles.
Cognaptus Insights
Industry thoughts, trends, and commentary.
TOGGLE or Die Trying: Giving LLM Compression a Spine
A mechanism-first reading of TOGGLE, a framework that turns LLM compression into a constrained engineering problem using temporal logic, Bayesian optimization, and explicit behavioral thresholds.
When Black Boxes Grow Teeth: Mapping What AI Can *Actually* Do
A case-first reading of PCML, a method for turning black-box agent behavior into interpretable probabilistic capability maps.
Artism, or How AI Learned to Critique Itself
A mechanism-first reading of Artism, a dual-engine AI framework that turns generative art into a self-critical loop rather than another novelty machine.
Delegating to the Almost-Aligned: When Misaligned AI Is Still the Rational Choice
A decision-theoretic guide to deciding when imperfectly aligned AI systems are still worth delegating to.
From Benchmarks to Beakers: Stress‑Testing LLMs as Scientific Co‑Scientists
A comparison-based reading of SDE, a benchmark that tests whether frontier LLMs can move from science quiz performance to iterative scientific discovery.
Long Thoughts, Short Bills: Distilling Mathematical Reasoning at Scale
Nemotron-Math shows that better mathematical reasoning supervision is not just more data, but a carefully engineered mix of reasoning depth, tool use, source diversity, filtering, and long-context training economics.
Mind-Reading Without Telepathy: Predictive Concept Decoders
A mechanism-first reading of Predictive Concept Decoders and why activation-based audit layers may matter more than model self-explanations.
Stepwise Think-Critique: Teaching LLMs to Doubt Themselves (Productively)
A close reading of Stepwise Think-Critique, a single-model approach that interleaves reasoning and self-critique to make mathematical reasoning more inspectable without pretending self-audit is already trust.
When Tokens Remember: Graphing the Ghosts in LLM Reasoning
A practical reading of CAGE, an attribution-graph method that audits not only which prompt evidence influenced an LLM answer, but how intermediate generations carried that influence forward.