Blog

9 posts

  • FeaturedOpinion

    AI Safety Needs Startups

    Why the best way to deploy safety at scale might be to sell it.

    Lysander Mawby

  • Research

    Less is more the same

    Quantisation costs our probes nothing, and cuts GPU time by 40% on Blackwell cards.

    Benedict Mullins

  • Engineering

    Is Your AI Hallucinating?

    How our white-box proxy model gives you a per-token hallucination score, including exactly what it costs.

    Adam Pattenden

  • Research

    Manifold Destiny

    Everything the model knows about a token is packed into the residual stream, and locally the model turns out to be using less than 1% of the stream for a single prompt.

    Benedict Mullins

  • Engineering

    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.

    Adam Pattenden

  • Research

    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.

    Adam Pattenden

  • Research

    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.

    Adam Pattenden

  • Engineering

    How We Detect AI Hallucinations in Real-Time

    Learn about the technical approach behind Telluvian's real-time hallucination detection, including probing classifiers, activation analysis, and token-level confidence scoring.

    Lysander Mawby

  • Opinion

    AI 2030: Our Generation’s Platform for Global AI Action

    Encode Justice’s platform for global AI action by 2030: five calls to world leaders, co-written by Lysander Mawby.

    Lysander Mawby and others