Andrew Feldman: AI Needs a Dinner Plate Chip, Not GPUs
Cerebras CEO Andrew Feldman explains why their 'dinner plate-sized' chip delivers 18x speed by solving AI's core data movement problem. Don't optimize, re-architect.
The best ideas from 30+ top podcasts, every week.
This episode features a panel discussion with Andrew Feldman (Cerebras) and Will Marshall (Planet Labs) about their companies' journeys going public. They delve into the operational realities, benefits, and challenges of IPOs, discuss the future of AI silicon architecture, and explore the concept of space-based data centers and planetary intelligence. The conversation also touches on broader trends in public market investor liquidity and the shifting sentiment around the optimal time for tech companies to go public.
Cerebras CEO Andrew Feldman explains why their 'dinner plate-sized' chip delivers 18x speed by solving AI's core data movement problem. Don't optimize, re-architect.
Andrew Feldman of Cerebras explains how 'dinner plate-sized' chips 18x faster than GPUs for AI prove radical architecture beats incremental upgrades.
Founders Andrew Feldman (Cerebras) and Will Marshall (Planet Labs) debate IPO value. Is it just admin 'garbage,' or does it unlock crucial customer trust?
Founders, rethink your IPO timeline. Public markets often create more wealth than private rounds. Learn from Planet Labs and challenge your VCs.
Forget 'stay private forever.' The All-In panel argues companies like Planet Labs see 10X growth *after* going public. Re-evaluate your IPO timeline.
Planet Labs CEO Will Marshall predicts most compute will move to space within 10 years, driven by falling launch costs and efficient solar power. Founders, watch this cost curve.
The week's best AI, tech, business, science, and culture podcasts in one short read. Free, every Sunday.
You get both newsletters, The Throughline and The Carry. No spam. Unsubscribe with one click.