To Nha Notes | Feb. 17, 2025, 8:50 a.m.
In short, here are the common AI engineering pitfalls:
Use generative AI when you don’t need generative AI
Gen AI isn’t a one-size-fits-all solution to all problems. Many problems don’t even need AI.
Confuse ‘bad product’ with ‘bad AI’
For many AI product, AI is the easy part, product is the hard part.
Start too complex
While fancy new frameworks and finetuning can be useful for many projects, they shouldn’t be your first course of action.
Over-index on early success
Initial success can be misleading. Going from demo-ready to production-ready can take much longer than getting to the first demo.
Forgo human evaluation
AI judges should be validated and correlated with systematic human evaluation.
Crowdsource use cases
Have a big-picture strategy to maximize return on investment.
https://huyenchip.com/2025/01/16/ai-engineering-pitfalls.html?utm_source=substack&utm_medium=email