
This Day in AI Podcast EP40: Open AI Dev Day Recap: Custom GPTs, GPT-4 Turbo, Assistants API Discussion & Test Drive
34 snips
Nov 10, 2023 Deep dive into OpenAI's latest offerings, including custom GPTs, GPT-4 Turbo, and Assistants API. Monetization challenges and the effectiveness of prompts and models are discussed. The limitations of GPT-4 Turbo and the use of embeddings and vector databases for text retrieval are explored. The significance of JSON output and the OpenAI Dev Day recap are also highlighted.
AI Snips
Chapters
Transcript
Episode notes
Reliable Data Retrieval
- Ensure consistent data retrieval for reliable custom GPT/agent experiences.
- Avoid relying solely on web searches due to manipulation risks and inconsistencies.
Data Privacy Concerns
- OpenAI's default setting for GPTs uses conversation data for training, including proprietary data.
- This contradicts their claims of not training on user data, raising concerns about data privacy.
OpenAI's Data Strategy
- OpenAI's strategy may involve using GPTs to gather real-world data, inaccessible through web crawls.
- They could leverage a store and user rankings to create a human-curated knowledge graph.
