← @bgSponge

Introducing Fusion in Devin Desktop & CLI

Summary

Cognition ships Fusion in Devin Desktop and CLI: a two-agent harness where a frontier lead plans and reviews while a cheaper sidekick executes, claiming up to 39% lower cost than peer harnesses on Fable and Astra coding benchmarks.

  1. Lead plus sidekick beats one-shot routing.

    Difficulty is unknown until exploration, so Fusion keeps frontier intelligence reviewing while a cost-effective model does the work.

    Fusion works around the common pitfalls of routing with a key idea: running two parallel agents

  2. Briefs preserve cache and control.

    Agents exchange briefs, results, and feedback instead of whole conversations, with the lead able to take over when the sidekick is out of depth.

  3. Price per task, not per token.

    Stronger leads and sidekicks can cut total session cost by delegating earlier, needing fewer correction rounds, and using tokens more efficiently.

    models (and model-harness combos) should be evaluated on price per task rather than price per token

  4. Harness tuning is pair-specific.

    How detailed briefs are, whether the sidekick may push back, and what exploration is delegated all depend on the lead–sidekick pairing.

  5. Recommended pairing: Fable 5.1 with SWE-2.

    Evaluations with Artificial Analysis and Vals AI show large cost cuts while scores stay near the frontier models alone.

    using more expensive models can make the entire system cheaper

Read the original ↗Save to your Sponge

Summarized with Sponge. Quotes are the author’s own words.

More from @bg

All readings →