Posts by apike@mastodon.social
 (DIR) Post #ATyxuJQCLEg7DV6sPw by apike@mastodon.social
       2023-03-25T18:25:49Z
       
       0 likes, 0 repeats
       
       @simon I’ve seen a lot of misunderstandings like that, even just stemming out of the nondeterministic nature of the models. So somebody will say “GPT-4 has this bad output if you input Y” when the actual discovery was “GPT-4 occasionally has this bad output if you input Y” which is less dramatic.
       
 (DIR) Post #AdiIi3X0oD8DcbqKlU by apike@mastodon.social
       2024-01-10T18:45:02Z
       
       0 likes, 0 repeats
       
       @simon I’m curious what your take is on the design of GPTs, and whether the "bot can't speak first" constraint signals a grander plan on OpenAI's part: https://allenpike.com/2024/chatbot-to-everything-engine