Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
Keyword tool-use scores falsely credit small Spanish security models; a cheap diagnostic ladder separates real tool calls.
1 stories, newest first · one card per story
Keyword tool-use scores falsely credit small Spanish security models; a cheap diagnostic ladder separates real tool calls.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views