|
|
|
|
|
|
by potatolicious
320 days ago
|
|
|
This feels like honestly the biggest gain/difference. I work on things that do a lot of tool calling, and the model hallucinating fake tools is a huge problem. Worse, sometimes the model will hallucinate a response directly without ever generating the tool call. The new training rewards that suppress hallucinations and tool-skipping hopefully push us in the right direction. |
|
|