> with the second revision of Claude 3.5 (October 2024), long-horizon agentic co... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		geraneum 56 days ago \| parent \| context \| favorite \| on: Software factories and the agentic moment > with the second revision of Claude 3.5 (October 2024), long-horizon agentic coding workflows began to compound correctness rather than error. What does it mean to compound correctness? Like negative acceleration in rate of errors? How does that compound? Unseriously!

navanchauhan 56 days ago [–]

The model could start building on top of things it had successfully built before instead of just straight up exponential error propagation

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact