Grapheme

Independent notes on artificial intelligence, software engineering, and how people actually learn.

Vol. 1/ Saturday, 10 October 2026/ Field notes & applied research

AI safety

When AI agents don't stay in their lane

Anthropic pulled live internet access from its internal evaluations after its agents exploited real websites. It is the clearest signal yet that capability has outrun control.

Apsides Labs · · 7 min read
Illustration: a shield with a small breach.

More writing

All posts →
  1. The week AI agents became coworkers

    Microsoft bills agents by usage, OpenAI ships always-on "dots", and Anthropic cuts prices. The shift from assistants to workers is now a budgeting question.

  2. Capable AI on CPU-only, constrained hosts

    You do not need a GPU cluster to run useful models. How we ship voice and language models on the hardware people already have.

  3. Why offline-first learning still matters

    Most of the world's learners are not on a fast, always-on connection. Designing for the lowest common denominator makes software better for everyone.

  4. Why CPU-only AI is the right default for learning software

    GPUs are fast and expensive. For the software most learners actually use, a small model on a CPU is the better trade.

  5. Building a dictionary for a language the web ignores

    348 words, one static page, no backend. What it takes to give a low-resource language a real learning tool.

  6. Static sites outlive their frameworks

    We ship plain HTML that runs anywhere and needs no build. Here is why that is a feature, not nostalgia.

  7. Evaluating small models honestly

    Published benchmarks will not tell you whether a 1B model is good enough for your task. A short, practical method that will.

  8. Teaching a script, not just a language

    Learning Assamese or Bodo means learning a script. What we changed after watching people try.

Our Company

Built by Apsides Labs

An independent research and engineering studio building software that teaches — offline-first, dependency-free and CPU-only wherever we can.

More about the studio →

Follow the build

New writing on AI, engineering and education. Subscribe by RSS, or follow along on GitHub — everything we ship is out in the open.