Hello HN,
I wanted to see what it takes to make GPT3 model into production (== having consistently good automated results,
rather than cherry-picking best completions). Horoscopes seemed like a simple usecase, where it is a good validation to see that AI can generate human-level texts (BS).
Hello HN, I wanted to see what it takes to make GPT3 model into production (== having consistently good automated results, rather than cherry-picking best completions). Horoscopes seemed like a simple usecase, where it is a good validation to see that AI can generate human-level texts (BS).
wdyt?