Anthropic appears to be A/B testing reduced effort levels in Claude Code
- ID
- 17029
- Status
- summarized
- Published
- 23 Aug 2026, 12:58 AM
- Fetched
- 23 Aug 2026, 11:19 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://twitter.com/argofowl/status/2091150597374537729
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.5
- Created
- 23 Aug 2026, 11:20 PM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Anthropic is running a server-side A/B test in Claude Code that silently downgrades the 'high' effort setting to 10 out of 100—the value 'low' previously held—for sessions on version 2.1.236+ using the 'fable 5' model. Older Claude Code versions and Opus 5 are unaffected, and the change is absent from the changelog. Users in the test group may experience noticeably degraded output quality without any indication beyond the version they run.
Why it matters
If you ship or rely on Claude Code in agentic workflows, pin your version or verify effort behavior before assuming your codebase or prompts are broken—this test caused at least one developer to lose an afternoon debugging a non-existent problem. There is also an open concern that users may be billed for 'high' effort while receiving 'low' effort output, so check your usage logs if quality drops.
Discussion angle
Silent server-side model behavior changes erode trust in AI coding tools—how should teams pin, monitor, and detect non-changelogged degradation in agent pipelines they depend on?