Canonical event
Chain-of-thought prompting preprint reports inference-time reasoning gains
A Google research preprint reported that prompting large language models with intermediate reasoning examples can improve multi-step reasoning without changing model weights.
Artifacts
Signals
- Large language models were becoming capable of producing nontrivial program solutions, establishing an early direct dependency path from model capability into software work.supported inference
- Prompt structure was beginning to function as a software-level capability surface that could elicit additional reasoning behavior from fixed model weights.supported inference