Nvidia GB200, every mention
13 scenes, the whole family · ← back to Nvidia GB200
tap a year for its mentions
every year anyone John Coogan 5
Verbatim, from the transcripts: the passages where Nvidia GB200 comes up
Meta Settles Addiction Suits, Tim Cook Signs Off After 15 Years, OpenAI’s Jalapeño Chip | Diet TBPN
- ▶ 21:11 unnamed speaker More useful inference throughput, per watt, than NVIDIA GB 200, GB 300 systems, while simultaneously cutting end-to-end latency, 1.7 to 3.6 x.
Big Companies Hiring Again, Anthropic's Open-Weight Position, Zuck Backs AI for All | Diet TBPN
- ▶ 28:59 unnamed speaker And as soon as you're a U S based company with a real data center with a bunch of NVL 72 in there, uh, you probably have registration and, you know, all sorts of just like business registrations where the government can reach out to you…
Cloudflare CEO Predicts AI Agents Will Outnumber Humans 1,000-to-1
- ▶ 11:15 unnamed speaker Uh, they can obviously go to their private cloud as well, and then you have, like, the new NVL-seventy-two models
SpaceX S-1, Anthropic Revenue Booms, OpenAI Cracks Erdős Problem | Diet TBPN
- ▶ 11:10 John Coogan So, uh, Tom Brown, co-founder of Anthropic says, we're expanding our partnership with SpaceX and we'll be scaling up GB 200 capacity on Colossus two throughout June. 2 times in the scene
Altman’s Testimony, AI SPV Drama, Ebay Rejects $GME Bid | Diet TBPN
- ▶ 25:56 unnamed speaker It's an NBL 72 that you're just like,
OpenAI Ends Side Quests, SF Housing Market is Back, Kalshi’s $1B Prize | Diet TBPN
- ▶ 26:49 unnamed speaker NVIDIA Xtreme co-design, revolutionized token cost, the GBNVL-CII is the inference king with a 50 X higher performance per watt on inference X by semi-analysis.
The Remarkable AGI Predictions of Daniel Gross
- ▶ 7:09 unnamed speaker NVIDIA's GB 200 NVL 72 server rack uses over 5000 copper cables. 2 times in the scene
Citrini Research’s viral piece, AI and the economy, 90s Nostalgia | Diet TBPN
- ▶ 29:42 unnamed speaker Those were real NVL 72 Ender.
FULL INTERVIEW: Dylan Patel Says We’re Still Underestimating AI
- ▶ 5:23 unnamed speaker Like, if it's, if it's a good, if the next version of Grok is a great chip, is it sitting next to the, you know, H 200, H 100 in the, in the rack, GB 200?
Clawdbot’s name change, Meta’s new pricing plan, Tyler’s 21st birthday | Diet TBPN
Wednesday’s Diet TBPN
- ▶ 22:59 unnamed speaker Like if you're building based off the H 100 chip, that's different than if you're building a data center based off GB 200.
DeepSeek, Stargate Update, Bees Do Enjoy Honey, Golden Retriever Maxxing, Bring on the Trilly
- ▶ 1:23:25 John Coogan A thousand, uh, GB 200 cluster for OpenAI's use. 3 times in the scene