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

Re:Anthropic appears to be A/B testing reduced effort levels... by owebmaster on Saturday August 22, 2026 @04:39PM (#49403673)

There is a theory that the verbosity and comments help getting better results with the current benchmarks. So the models are theoretically getting better but in practice they are getting worse.

[ Parent | on HN ]

Re:Anthropic appears to be A/B testing reduced effort levels... by gwerbin on Saturday August 22, 2026 @10:16PM (#49405626)

I believe they are genuinely getting better for fully autonomous tasks. Anthropic seems to have gone all in on this, at the expense of more typical usage patterns.

[ Parent | on HN ]