AIThe Decoder1h ago

Anthropic engineer explains why Claude's writing got worse although

Anthropic engineer explains why Claude's writing got worse although the model got smarter

Anthropic engineer explains why Claude's writing got worse although

Anthropic employee Jackson Kernion explains why newer Claude models write so oddly. Optimizing for math, code, and technical explanations aimed at other AI models has created a style that sounds like "overly-dense info dumps" to humans. Opus 5.5 tries to fix this, but Opus 4.6…

Read full article

Source: The Decoder · Opens in new tab