Comment by geraneum
19 days ago
> 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!
The model could start building on top of things it had successfully built before instead of just straight up exponential error propagation