---
format: "aidr-story-markdown/v1"
id: "33e354a2033bc20bc8f5451efbca42b8d364b08b079a645f30329b93df8e976d"
canonical_url: "https://aidr.today/33e354a2?lang=en"
title: "Anthropic appears to be A/B testing reduced effort levels in Claude Code"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-22T16:58:49.000Z"
category: "Products"
topics: ["anthropic","claude","coding","agent"]
source_urls: ["https://twitter.com/argofowl/status/2091150597374537729","https://news.ycombinator.com/item?id=49401549"]
summary: "update: it's server-side, not the app anthropic enrols fable 5 sessions on claude code 2.1.236+ into an experiment that shrinks the effort scale, older versions and opus 5 are left alone probably an a/b test, so not everyone will see it if \"high\" feels like \"low\" for you,"
---

# Anthropic appears to be A/B testing reduced effort levels in Claude Code

> [Open the canonical story](<https://aidr.today/33e354a2?lang=en>)

**Published:** 2026-08-22T16:58:49.000Z
**Category:** Products
**Topics:** anthropic, claude, coding, agent

## Summary

update: it's server\-side, not the app anthropic enrols fable 5 sessions on claude code 2\.1\.236\+ into an experiment that shrinks the effort scale, older versions and opus 5 are left alone probably an a/b test, so not everyone will see it if "high" feels like "low" for you,

## Sources

- [Story source](<https://twitter.com/argofowl/status/2091150597374537729>)
- [Discussion](<https://news.ycombinator.com/item?id=49401549>)

