Compute Cluster
topic on 5 shows · 6 statements across 6 episodes
More or Less 
BG2 Pod 
Invest Like the Best 
the MAD Podcast 
the a16z Podcast
6 statements about Compute Cluster, every show
Dan Fu: Deployed AI models lag cluster infrastructure by 1–2 years
“The models that we see today that we can play with today have been pre-trained on clusters that were built out a year or two ago. Because, you know, you need enough time to get the cluster running. You need enough time to do the large pre-training run. And the…”
Patel: Massive AI Researcher Pay Is Justified by Huge Cluster Costs
“I think it's, like, tremendously hilarious that people are like, oh my god, this person's getting paid a billion dollars? It is infeasible. It's like, how could this person possibly be worth that much? Well, they're running the experiments on chips that cost, …”
Patel: An AI training cluster can run 100,000 inference copies simultaneously
“It is the case that for the amount of compute it costs to train a system if you like set up a cluster to train a system you can usually run a 100,000 copies of that model at typical token speeds on that same cluster.”
Gerstner: Superior reasoning architecture beats raw compute scale in AI
“Like you can have the best computers and chips and biggest cluster in the world. But if you don't get the architecture right around your reasoning model and the other guy does, they're probably going to win.”
Sam Lessin: Massive AI compute clusters are just billionaire dick-measuring contests
“It's the ultimate pissing context. This is like, instead of having sports cars, you now have large compute clusters as a dick measuring competition.”