Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Yann LeCun, Pioneer of AI, Thinks Today's LLM's Are Nearly Obsolete. Parent comment
"Shown are the sum of prompt and completion tokens per model, normalized using the GPT-4 tokenizer."
Also, it ranks the use of Llama that is provided by cloud providers (for example, AWS Lamda).
I get that OpenRouter is imperfect but its a good proxy to objectively make a claim that an LLM is "the weakest ever"
There are no comments on this comment yet.
"Shown are the sum of prompt and completion tokens per model, normalized using the GPT-4 tokenizer."
Also, it ranks the use of Llama that is provided by cloud providers (for example, AWS Lamda).
I get that OpenRouter is imperfect but its a good proxy to objectively make a claim that an LLM is "the weakest ever"