announcing our brand new function calling guide @openai!
we heard your feedback and made some key changes:
- 50% shorter & clearer
- new best practices (more on this below 👇)
- in-doc function generation (!)
- fully-functional example w/ weather API
check it out and let me know what you think! we love feedback 💪
🤖 I’m prepping several classes on LLM evaluation for AI products right now. If you’re building in this space, these are the 3 best resources to get started, and I recommend reading them in this order:
1. “Task-Specific LLM Evals that Do & Don’t Work” by @eugeneyaneugeneyan.com/writing/evals/
2. “Your AI Product Needs Evals” by @HamelHusainhamel.dev/blog/posts/eva…
3. “Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences” by @sh_reya et al. arxiv.org/abs/2404.12272
Read them, internalize the key points, and keep them in mind while building, building, and building. Your AI products will be far better—and you’ll increase your chances of becoming extremely wealthy 🤑