
First-hand detail on how OpenAI's own API team runs agentic engineering at scale — parallel fleets, cutting code review from 15 to 2-3 minutes, and why building thin scaffolding around models is a losing bet as capabilities advance.
“95% of engineers use codecs. 100% of our PRs are reviewed by codecs.”
Sherwin Wu
“It literally feels like we're wizards casting all these spells.”
Sherwin Wu
“So I think we might actually enter into a golden age of B2B sass.”
Sherwin Wu
“The models will eat your scaffolding for breakfast.”
Sherwin Wu
“Make sure you're building for where the models are going and not where they are today.”
Sherwin Wu
podcastThe 100-person AI lab that became Anthropic and Google's secret weapon | Edwin Chen (Surge AI)
podcastWhy humans are AI’s biggest bottleneck (and what’s coming in 2026) | Alexander Embiricos (OpenAI Codex Product Lead)
podcastThe coming AI security crisis (and what to do about it) | Sander Schulhoff
podcastWhy most AI products fail: Lessons from 50+ AI deployments at OpenAI, Google, and Amazon
podcastWhy humans are AI’s biggest bottleneck (and what’s coming in 2026) | Alexander Embiricos (OpenAI Codex Product Lead)Lenny Rachitsky
podcastAI’s third era: the rise of persistent AI coworkers | Tara Seshan (OpenAI’s product lead)Lenny Rachitsky
podcastWhat happens after coding is solved? | Fiona Fung (Manager of the Claude Code and Cowork Teams)Lenny RachitskyChecking sign-in…
Loading comments…