Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

The situation

ai/), an experiment in making one AI system out of a pool of open-weight models rather than choosing a single model and using it for every task. 7 and others, and ran them on the same evaluations.

The significance

Then I measured what would happen if, for each problem, you somehow knew in advance which models would be useful and how their outputs should be combined. That hypothetical system performed substantially better than any individual model in the pool.

The context

Of course, it is not something you can actually deploy because it relies on knowing which decisions were good after seeing the result

Where this fits in Signal Ledger

Related coverage from the Technology desk.

• Selfie for sign-in: a new, easy way to access your Google Account
• From Evaluation to Guardrails: What We Brought to ACM FAccT 2026
• Building on ATProto

The read

That hypothetical system performed substantially better than any individual model in the pool. For each request, Echo decides how much computation to allocate.