top | item 45854136 (no title) floodfx | 3 months ago Why are completion tokens more with image prompts yet the text output was about the same? discuss order hn newest cma|3 months ago Some multimodal models may have a hidden captioning step that may take completion tokens, others work on a fully native representation, and some do both I think. Garlef|3 months ago "Thinking" Mode nunodonato|3 months ago it doesn't say that anywhere.
cma|3 months ago Some multimodal models may have a hidden captioning step that may take completion tokens, others work on a fully native representation, and some do both I think.
cma|3 months ago
Garlef|3 months ago
nunodonato|3 months ago