| ▲ | jey an hour ago | |
This seems to be incorporated into current LLM generations already -- when code execution is enabled both GPT-5.x and Claude 4.x automatically seem to execute Python code to help with reasoning steps. | ||
| ▲ | Esophagus4 9 minutes ago | parent | next [-] | |
Same with CoT prompting. If you compare the outputs of a CoT input vs a control input, the outputs will have the reasoning step either way for the current generation of models. | ||
| ▲ | logicprog an hour ago | parent | prev [-] | |
Yeah, this is honestly one of the coolest developments of new models. | ||