One modality
Text-only prompt with zero-shot Chain-of-Thought prompt engineering 🥳
Just like people:
- asking an LLM to go slowly and step by step avoids errors
- providing distraction (images to consider, etc) increases errors
Reference
- Notes
- llm
- Test Driving ChatGPT-4o
-
Permalink to
2024.NTE.104 - Edit
| ← Previous | Next → |
| How to converse online via hello@manuelmoreale.com (Manuel Moreale) | Note on Building Personal and Organizational Prestige via Irrational Exuberance |