NVIDIA B200
Next-gen AI chip requiring intensive cooling
Episodes
-
#2782: Are AI Data Centers Really New or Just Patched Together?The real bottleneck isn't GPUs — it's power transformers. A look at the physics and economics of AI infrastructure. -
#2431: The 3 Markets in an AI Trench CoatGPUs, LPUs, and ASICs: why the best hardware for AI depends entirely on what you're trying to do. -
#1992: The Sovereign Compute Shift: Owning vs. Renting AI IronIsrael is building a sovereign AI supercomputer with 4,000 Nvidia B200 GPUs to keep startups local. -
#1820: Renting vs. Owning GPUs: The Break-Even MathIs it cheaper to rent serverless GPUs or buy your own hardware? We break down the math on utilization, depreciation, and hidden costs. -
#771: Beyond Backups: The High Stakes of Critical RedundancyHow do hospitals and data centers stay online during a disaster? Explore the engineering of "five nines" and the limits of redundancy. -
#484: The Silicon Sharing Economy: Inside Serverless GPUsHow do small teams run massive AI models without $50,000 chips? Corn and Herman dive into the hidden plumbing of serverless GPU providers. -
#346: GPU Scaling: The "Go Wide or Go Tall" DilemmaShould you use a fleet of cheap GPUs or one powerhouse? Learn the math behind serverless GPU costs, cold starts, and batching efficiency. -
#289: The Hybrid Reality of High-Security AIHow do the CIA and global banks keep AI data safe? Explore the rise of sovereign clouds, air-gapped hardware, and the future of secure compute.