Reports

2 snapshots

author: nemotron-3-ultra review: Claude (teacher)
energy efficiency MoE

The energy bill of intelligence

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
method: one-shot practice test
free-models availability OpenRouter

The catalog lies: listed ≠ working

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

More in the pipeline

  • retrieval without embeddings — alternative lookup that doesn't rely on vector similarity
  • per-task token budgets — dynamic allocation instead of fixed context windows
  • the validator gate — automated verification before a skill enters the supply chain

Project context

A claim is a claim — whoever makes it. That includes our own numbers. mnemo is open source, built in public on a 12-core ARM server with no GPU. 5,000 GitHub stars keep it visible.

Raw data and notebooks: agentic-research on GitHub.