Blog
Writing on hallucination detection, mechanistic interpretability, and building AI systems you can trust.
Is Your AI Hallucinating?
How our white-box proxy model gives you a per-token hallucination score, including exactly what it costs.
Why AI Companies Will Have to Embrace Manifold Learning
Why manifold learning matters for AI companies, from the manifold hypothesis to intrinsic dimensionality in transformer hidden states.
AI Portal
Why AI inference costs keep rising despite falling token prices, and how mechanistic interpretability techniques like routing and prompt compression can cut them without sacrificing quality.
The Two-Neighbour Method: How to Measure a Dataset’s “True” Dimensions
How many intrinsic dimensions does your data really have? An introduction to twoNN and what it reveals about a transformer's residual stream.
What is Mechanistic Interpretability?
Modern large language models are immense black boxes, yet they still represent internal features in a standard way we can begin to understand.
AI Safety Needs Startups
Why the best way to deploy safety at scale might be to sell it.
How We Detect AI Hallucinations in Real-Time
Learn about the technical approach behind Scanf's real-time hallucination detection, including probing classifiers, activation analysis, and token-level confidence scoring.