StarZero Try the podcast clipper →

Time To First Token

topic on 2 shows · 2 statements across 2 episodes

the Y Combinator Startup Podcast Latent Space

2 statements about Time To First Token, every show

Y COMBINATOR Assertion Not publicly verifiable
Srinivas: Perplexity maintains the fastest time-to-first-token despite performing live web searches
“We focus on speed, time to first token on app or web, like we're still the fastest despite doing search.”
Aravind Srinivas Jul 11, 2025 ▶ 23:21 Aravind Srinivas: Perplexity's Race to Build Agentic Search · Y Combinator
LATENT SPACE Assertion Not checkable as stated
Colvin: Major AI lab cut time-to-first-token 20% upgrading to Pydantic v2
“I can't say which one, but one of the big foundational model companies, when they upgraded from Pydantic v one to v two, their number one internal metric of performance is time to first token That went down by 20%.”
Samuel Colvin Feb 6, 2025 ▶ 6:07 Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more