Just compared Claude-Sonnet-3.5 with OpenAI's o1 on a CLS task – classifying text inputs from US short stories with regard to focalization. Turns out, Sonnet doesn't recognize zero focalization and achieved an F1-score of 0.47, while o1 performed better with 0.69. Not bad - but problematic, as the hidden tokens of the optimizer (?) from o1 would be of particular interest.
[#]CLS #AI #ClaudeSonnet #OpenAI's_o1 #TextClassification #Focalization
=> More informations about this toot | View the thread | More toots from axelpichler@fedihum.org
=> View cls tag | View ai tag | View claudesonnet tag | View openai tag | View textclassification tag | View focalization tag This content has been proxied by September (3851b).Proxy Information
text/gemini