Gregory's Server@dbreunig running a benchmark that processes a long essay and records the input token count for different models could be interesting though
|
Top-level
 @dbreunig running a benchmark that processes a long essay and records the input token count for different models could be interesting though 1 comment
|
@simon Someone's done it: https://medium.com/@disparate-ai/not-all-tokens-are-created-equal-7347d549af4d