A question I have, with the type { output: string }, would the model not become a LLM? And if it does, shouldn’t it cost the same as a LLM for output?
I don’t see this as an option in their websiteYou could theoretically ask “what is the next appropriate character?” and add the entire ascii charset but i doubt it’d work well and you’d be implementing autoregressive churn across network latency…
whazor · · focus · HN ↗
speedping · · focus · HN ↗
You could theoretically ask “what is the next appropriate character?” and add the entire ascii charset but i doubt it’d work well and you’d be implementing autoregressive churn across network latency…