Mike is an experienced Product Manager who focuses on all the “non-development” areas of My AskAI, from finance and customer success to product design, copywriting, testing and more.
Everyone obsesses over AI model "benchmarks" and "performance metrics".
Most people would gain far more from improving their prompting and instruction of these models.
Case in point:
- We adopted the new OpenAI GPT-4o model a few weeks ago and initially saw 2x as many "unanswerable" questions.
- Instead of looking for different models, we took the time to re-engineer our prompts to fit the model.
- Now we get way better results than we had even before.