MechanismAudio · 3:15 — 4:14

Wafer-scale engineering was the right architectural bet because radical improvement requires radical architectural difference, not incremental modification of the GPU.

Feldman explains Cerebras's bet on wafer-scale chips: to be 15-20x faster than GPUs, you cannot make minor modifications — you need a fundamentally different architecture, which is why Cerebras built a dinner-plate-sized chip. ✦ AI generated

Andrew Feldman · No Priors · 2026-05-21 · original ↗

Share card ↓Export .md Export .txt

plays this moment only · 3:15 — 4:14

Elicited by

“What shifted in the last year and a half? Was it the ramp in manufacturing? Was it a new chip design? Was it something else?”

I think to be radically better, right? You can't build something that is a similar architecture, right? You're not going to get 15 or 20 times better than the GPU with a minor modification to their architecture. And that's probably true across the board, that if you're going to aspire to a radical improvement, your design has to be different. And from the beginning, we chose wafer scale, which means we build a 46,000 square millimeter chip, a chip the size of a dinner plate, whereas everybody else is building chips the size of postage stamps. They told us we were out of our mind, it would never work.

verbatim transcript · starts at 3:15

◉ Andrew Feldman

Around this claim

Mechanism · 1

Speed is the fundamental value driver in AI inference — slow inference has no market, just like slow search or dial-up internet had no market.Andrew Feldman · No Priors · conf 90%

In practice · 2

Current computers and phones are 20-year-old designs completely unsuitable for AI, and HARK is designing radical new hardware to replace them.Brett Adcock · My First Million · conf 70%The real competitive advantage from AI comes from redesigning entire companies around the technology, not superficial adoption—comparing it to how Ford redesigned factories for electricity rather than just swapping engines.Ali Massa · a16z Podcast · conf 70%

This moment responds to

explains mechanism → Cerebras survived a brutal period of being ahead of the market — building something technically impossible that nobody wanted — by winning supercomputer customers and a sovereign strategic partner that bridged the chasm to mainstream demand.Andrew Feldman · No Priors explains mechanism → Current computers and phones are 20-year-old designs completely unsuitable for AI, and HARK is designing radical new hardware to replace them.Brett Adcock · My First Million gives example → For the world to be radically transformed, AIs only need to be superhuman at verifiable R&D (chips, fabs, robotics, AI research itself); being great at intangible domains like politics and negotiation is not required.Ryan Greenblatt · Dwarkesh Podcast supports → Current phones and computers are fundamentally the wrong interface for AI—HARK is designing a radical new AI-native device to replace them, not an incremental improvement like AI glasses.Brett Adcock · My First Million