We've fine-tuned GPT-2 using human feedback for tasks such as summarizing articles, matching the preferences of human labelers (if not always our own). We're hoping this brings safety methods closer to machines learning values by talking with humans.https://openai.com/blog/fine-tuning-gpt-2/ …
Is there a fast way to try these advances online? Summarization seems to be pretty easy to test on a website
09:04 - 19. ruj 2019.
0 replies
0 proslijeđenih tweetova
1 korisnik označava da mu se sviđa
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.