cd /news/ai-products/anthropic-appears-to-be-a-b-testing-… · home topics ai-products article
[ARTICLE · art-107225] src=twitter.com ↗ pub= topic=ai-products verified=true sentiment=↓ negative

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

Anthropic is A/B testing reduced effort levels in Claude Code, affecting sessions on version 2.1.236+ with the change applied server-side. The experiment shrinks the effort scale, while older versions and Opus 5 remain unchanged, and not all users will see the change.

read1 min views1 publishedAug 22, 2026
Anthropic appears to be A/B testing reduced effort levels in Claude Code
Image: source

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, you're in the test group holy fuck anthropic, you guys are unbearable sometimes

── more in #ai-products 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/anthropic-appears-to…] indexed:0 read:1min 2026-08-22 ·