Ep 24: OpenAI Head of DevRel Logan Kilpatrick on The Best ChatGPT Use Cases, Future of Agents, and Google Gemini
Unsupervised Learning
Fine Tuning and Model Choice for Improved Performance
Fine tuning the GBT3.5 model can significantly enhance its performance, especially for more complicated requests. However, for complex requests with more instructions, switching over to GBT4 is recommended as it shows better performance. With the recent price drops, GBT4 has become more affordable, leading many to opt for it rather than investing extra effort in fine tuning GBT3.5. Nonetheless, fine tuning GBT3.5 has shown to achieve GBT4 level performance for early customers, leading to cost savings and exciting outcomes.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
