research · mnemo project
Teacher-reviewed research from the mnemo project. Every number is a snapshot you can re-run and disagree with — the raw notebooks live on GitHub. Confabulations get caught; the ones we couldn't verify are marked as such.
Read the published reports ↓“A claim is a claim — whoever makes it.”
Every card begins with its date and method. The route back to the raw work stays visible.
published snapshots
A dated record is more useful than a timeless-looking metric. Filter the small archive by topic, or inspect the source directly.
Estimated energy per token across the free-model swarm vs. a frontier model — EcoLogits + ML.ENERGY methodology, honest error bars. The swarm runs 50–200× leaner; the teacher review cuts that headline down to an upper bound and says why.
Read on GitHub →The OpenRouter catalog listed 22 free models. A one-sentence practice test found that listed is not working — exhausted pools, silent hangs, and four things ‘everyone knows’ that the API response contradicts.
Snapshot on GitHub →next in the pipeline
More in the pipeline — retrieval without embeddings, per-task token budgets, the validator gate.