GPT-3を活用ã™ã‚‹ã“ã¨ã§è‡ªç„¶è¨€èªžã‹ã‚‰ã‚³ãƒ¼ãƒ‰ã‚’自動生æˆï½œSangmin Ahnã“ã‚“ã«ã¡ã¯ã€Choimirai School ã®ã‚µãƒ³ãƒŸãƒ³ã§ã™ã€‚ ã€ä¸»è¦ãªã‚¢ãƒƒãƒ—デート】 （2020.07.22）グーグルシート用ã®é–¢æ•°ã€gpt3() ã‚’è¿½åŠ ï¼ˆ2020.07.22）Repl.it ã®ã‚³ãƒ¼ãƒ‰ä»•æ§˜èª¬æ˜Žãƒ„ãƒ¼ãƒ«ã‚’è¿½åŠ ï¼ˆ2020.07.20）Reactã§TODOリストã®ã‚¢ãƒ—リを生æˆã™ã‚‹å‹•ç”»ã‚’è¿½åŠ 0 ã¯ã˜ã‚ã«2020å¹´5月28æ—¥ã«ç™ºè¡¨ã•ã‚ŒãŸã€GPT-3。 GPT-3: Language Models are Few-Shot Learners, by @notTomBrown et al. “We train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its
{{#tags}}- {{label}}
{{/tags}}