Team Goes From Zero to Tape-Out in 5 Months, Discloses AI-Accelerator Hardware at All-In Conf
Konstantine · x · 2026-09-17
Following the All-In Podcast conference, Naveen Rao shared progress on his hardware project: the team formed from scratch in January and reached tape-out in just 5 months, with hardware back over the summer.
He credits AI for enabling much tighter research loops and faster execution, calling it the first large-scale demonstration of a "causal, physical" system (post truncated, details incomplete). It's a compute-chip development update; no full architecture or benchmark data is public yet.
Related event: Naveen Rao's Chip Startup Tapes Out in 5 Months, Runs AI at Under 900nJ(5 posts)→
More from Infra
- BofA: B200 and H100 GPU rental prices hit new highs, up 47% and 31% YTD — TheZachMueller · 2026-11-02
- vikhyat predicts alternating compute oversupply and undersupply on the road to AGI — TheZachMueller · 2026-11-02
- PyTorch Mac downloads hit 3.29M in October, up 20.5% MoM — LysandreJik · 2026-11-02
- CVSS 9.8 ingress-nginx flaw lets unauthenticated attackers get RCE and steal cluster Secrets — evilsocket · 2026-11-02
- RAM prices tripled, so Tesla cut a third of memory from Optimus's brain — aakashgupta · 2026-11-02
- Liquid AI's 1.7B LFM3 becomes first local model to nail live fixtures lookup on a MacBook — NielsRogge · 2026-11-02