DigestAI news desk

Cut through the AI noise.

Developing story · 6 episodes · 29 Sept to 26 Oct

Google Unveils Harness Framework for Self Improving Agents

The saga tracks Google's development and open-sourcing of the Harness framework, which enables AI agents to recursively reorganize prompts and tools while preventing overfitting. The latest episode confirms the framework's release, providing a robust solution for self-improving agents that avoids memorizing tests.

  1. Ponytail prompt may reduce Claude Code output to 23 lines

    A new prompt engineering method called "Ponytail" aims to make AI coding agents like Claude Code, Cursor, and Windsurf produce leaner, more efficient code. Developed by engineer Dietrich Gebert, the…

    1 source
  2. Coding agent harnesses triple token costs without boosting benchmark scores, study finds

    Complex harnesses for coding agents inflate token bills by up to three times while barely improving benchmark performance over minimal setups, according to a study by researchers Liu and Han at…

    1 source
  3. Google open-sources Harness² for self-improving AI agents without retraining

    Google Research has released Harness², an open-source framework that lets AI agents improve their own prompts, tools, and scripts through recursive loops—without altering the underlying model. The…

    2 sources
  4. Google Cloud AI Research open-sources Harness² recursive agent framework

    Google Cloud AI Research released Harness², an open‑source recursive agent harnessing framework version 0.1.0. The framework adds eight editable harness components—system prompt, guardrails, memory,…

    1 source
  5. Google researchers find way to prevent self-improving AI agents from memorizing tests

    Self‑improving AI agents risk memorizing the tests they run, which can hurt performance on new tasks. A new paper from Google Cloud AI Research and several universities proposes Regularized…

    1 source
  6. Google Research open-sources RRSI for self-improving AI agents without overfitting

    Google Research, alongside UNC-Chapel Hill, Stanford, and Washington University in St. Louis, has released RRSI (Regularized Recursive Self-Improvement), an open-source framework that lets AI agents…

    3 sources primary source
Who and what
Google ResearchUNC-Chapel HillStanfordWashington University in St. LouisGoogleGoogle Cloud AI ResearchNvidiaNorthwestern UniversityTypeSafe AIMetaShandong UniversityZhipu AI