Anthropic appears to be A/B testing reduced effort levels in Claude Code
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 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,
Summary
Anthropic is conducting an A/B test on its Claude Code system, adjusting effort levels for some users while leaving others on older versions. This change could impact how developers interact with the tool, making it essential for users to be aware of potential differences in experience.
Comments (185 of ) ⌛