← Latest products

I trained a language model that thinks the capital of Japan is Paris

DIMBA II: a 288M-parameter masked-diffusion language model on a bidirectional Mamba-2 backbone. What worked, what failed, and what we'd do with real compute.

Visit hamiltonianresearch.xyzexternal site

Reactions (1)

Similar products

by description similarity

  1. "Be horse."

    boesch.dev

    a diffusion language model on an M2 Air

    Hacker News10 pts

  2. Language Model Builder (an app to learn about and build models)

    languagemodelbuilder.com

    Hacker News17 pts

  3. Monadic Chat

    yohasebe.github.io

    A Docker-Based Framework for AI Interaction

    Hacker News17 pts

  4. Tiny Diffusion

    github.com

    A character-level text diffusion model from scratch

    Hacker News172 pts

  5. I made a state machine framework for guided conversations with LLMs

    github.com

    GoalChain for goal-orientated LLM conversation flows

    Hacker News19 pts