Oliver Wang: Nano Banana exceeded initial LMSYS Chatbot Arena query capacity
Oliver Wang · Google DeepMind Developers: How Nano Banana Was Made · Oct 28, 2025 · at 2:28
Oliver Wang, Principal Scientist at Google DeepMind, discusses user demand and server scaling during the early launch of the Nano Banana image model on LMSYS Chatbot Arena.
0:00 / 0:12exact quote · 12.3s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“What we saw was that we budgeted like, you know, a comparable amount of queries per second as we had for our previous models that were on Ella Marina. And we had to keep upping that number as people were going to Ella Marina to use the model.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Oliver Wang
Wang: A single AI model will never satisfy all use cases
“I definitely don't think that, that the broad amount of use cases will be fully satisfied by one model at any point. So I think that there will always be a diversity of models. Some, like I'll give you an example, but some, you know, we could optimize for inst…”
Oliver Wang: Great art is often in-distribution relative to prior art
“I think that out of distribution sample, that is a little bit too restrictive. I think a lot of great art is actually in distribution for art that occurred before it.”
Oliver Wang: Human intent is the defining element of art
“Like to me, I think that the most important thing for art is intent. And so the, what is generated from these models is, is a tool to allow people to create art.”
Wang: Generative AI can solve visual problems using 2D projections
“I think we can solve almost all the problems, if not all the problems, working on the projection of the three-D world directly, and letting the models learn the latent world representations.”
Oliver Wang: AI image models must raise worst-case output quality
“Every model can cherry pick images that look perfect. So like now I think the real question is like how expressible is this model and what's the worst image you would get given what you're trying to do? So I think by raising the quality of the worst image We r…”