Fragments: November 20
Source: Martin Fowler ·
Marcus Borg recounts an experiment to investigate if healthy code was cheaper for agents to review . Between a typical unhealthy pull request (CodeHealth 2.8) and a typical healthy one (9.7), that adds up to 22 to 35%. The measures of health come from CodeScene. The experiment looked at three LLMs, 465 pull requests on 246 open source repositories. Each pull request was put through a review and fix pipeline involving five agents. They also looked at which code smells led to increased costs: they highlighted Complex Method and Complex Conditional from the smells identified by CodeScene. Another
Featured in these lists
-
Interesting Web Discoveries (2026-W47)Surf list →
Tech essay · Martin Fowler · 8 discoveries
Frequently Asked Questions
What is Fragments: November 20?
Fragments: November 20 is a article discovery curated from Martin Fowler. Marcus Borg recounts an experiment to investigate if healthy code was cheaper for agents to review . Between a typical unhealthy pull request (CodeHealth 2.8) and a typical…
How can I access or experience this?
You can experience this content directly on its original host (Martin Fowler) by clicking the "Open Original" button.
Where does this content come from?
Curated from Martin Fowler by the OnSuggest team to surface the most interesting and serendipitous content on the web.
More like this
All Technology discoveries →Welcome Inkling 2 Mini, Cutting-edge Performance for your Local Setup
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Can AI help scientists identify promising drug candidates?
MedChemBench evaluates how well AI models interpret molecular structures, reason from experimental evidence, and select compounds in early drug discovery.
Hebbia sees improvements in financial research with GPT-6 Astra
Hebbia tested GPT-6 Astra for financial research. Its prerelease evaluations found gains in source coverage, citation relevance, and presentation quality.
Combatting adversarial distillation
OpenAI’s layered approach to adversarial distillation combines model training, safeguards, detection, and enforcement to protect against capability extraction.
How to securely connect internal Cloud Run MCP servers to Gemini Enterprise
How to connect Gemini Enterprise privately to internal StreamableHTTP MCP servers on Cloud Run using Egress Agent Gateway, Private Service Connect, FQDN-scoped Private Cloud DNS, and dual-header OAuth 2.0 authentication.
How to handle user, connector, and agent auth in Gemini Enterprise with a custom UI
When building a custom enterprise UI on top of Gemini Enterprise's :streamAssist API, developers must manually implement three core authentication layers. These include authenticating users or workloads via Google Identity or Workforce/Workload Identity Federation, managing third-party 3-legged OAuth (3LO) for Federated Connectors through the Keystore, and configuring on-demand per-tool OAuth for custom ADK agents using Vertex AI Agent Engine and GCP Auth Manager.