Hu: Voice AI Startups Meta-Prompt with Frontier Models Before Distillation
Diana Hu · State-Of-The-Art Prompting For AI Agents · Y Combinator · May 30, 2025 · at 11:12
Y Combinator partner Diana Hu explains how AI agent startups optimize latency by refining prompts on frontier models before deploying on smaller models.
0:00 / 0:51exact quote · 51.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I think that's a common pattern sometimes for companies when they need to get responses from elements, elements in their product a lot quicker. They do the meta-prompting with a bigger, beefier model, any of the, I don't know, hundreds of billions of parameters plus models like I guess, cloud four, 3.7, or your GPT-O three, and they do this meta-prompting, and then they have a very good working one that Then they use into the distilled model, so they use it on, ah, for example, an FRO, and it ends up working pretty well, specifically sometimes for, ah, voice AI agents, companies, because, ah, latency is very important to, ah, get this whole Turing test to pass, because if you have too much pause before, before the agent responds, I think humans can detect something is off, so they use a faster model”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Diana Hu
Diana Hu: Supabase is the default backend recommendation across all LLMs
“Whenever someone asks how to set up anything that you need, some sort of backend, Firebase type of transaction, the default answer from all the LLMs is actually a Superbase.”
Hu: Anthropic surpasses OpenAI as top API for YC applicants
“And, shockingly, in this batch, the number one API is actually Anthropic. It came out a bit more than OpenAI, which who would have thought?”
Diana Hu: AI's future Google- and Facebook-scale startups have not started yet
“Startups like the future Facebook or the future Google are yet to be started because those come in in the deployment phase, because right now I think these things, things are still getting built up.”
Hu: A YC startup's 8B model beat OpenAI on healthcare benchmarks
“There's this particular YCE startup that told me that they collected the best data set for healthcare. And they ended up performing better than OpenAI and a lot of the benchmarks for healthcare with only eight billion parameters.”
Hu: Cursor scaled from $1M to $100M revenue in one year
“We've seen crazy growth unlike anything, only possible with, right now with AI, like all these companies that we work with, zero to twelve million in 12 months. The cursor story where they went zero to one in one year, the next one to a hundred. This is, like,…”