The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 24 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Fruchter: Genie 3 generates environments without explicit 3D representations
“One thing that we didn't want to do, and we didn't want to build an explicit representation, right? So there are definitely methods that are able to achieve consistency, and they did that through an explicit, some three, you know, their nerves, and other metho…”
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…”
Parker-Holder: Genie 3 terrain physics emerge from scale, not explicit logic
“And I think that that really is the property of scale and breadth of training. So this is very much like an emergent thing. I don't think there's anything Like really specific we do for this, right?”
Fruchter: Genie 3 is a research preview, not a commercial product
“Gini Free is pretty much a research preview, right? It's not something we are releasing at this point.”
Parker-Holder: DeepMind targeted minute-plus spatial memory for Genie 3
“And then for Genie three, we basically went much more ambitious on the same sort of approach, right? And we made it like a headline goal for ourselves. It's like, can we make the memory be what it is, right? We said we want minute plus memory and real time and…”
Parker-Holder: Genie 3 combines real-world data with simulation for robotics
“Really what we think with Genie three is it's the best of both, right? Because you're taking a real world data driven approach, right? But then you've got the ability to learn in simulation. So It kind of combines the good parts of each of those. And so that's…”
Brichtova: AI character consistency evals require testing on familiar faces
“So when we're developing this model, we actually started out doing character consistency evals and faces we didn't know, and it doesn't tell you anything. And then we started testing it on ourselves and quickly realized like, okay, this is what you need to do …”
Oliver Wang: DeepMind has not solved combining simple and professional AI UIs
“We haven't exactly figured out how to enable both of those yet.”
Brichtova: DeepMind will not build specialized architecture software
“We're probably not going to go build a software for an architecture firm. My dad is an architect and he would probably love that. But I don't think that's something that we will do, but somebody should go and do that.”
Wang: Artists want AI models to infer intent, which models now do better
“Really what an artist wants when they want to do something is they want the intent to be understood. And I think that, that these AI models are getting better at understanding the intent of users. So often when you ask text queries now, the model gets what you…”
Wang: AI models will solve complex multi-person scenes without dedicated pose interfaces
“Yeah, I think in that case, I wouldn't spend a ton of time building a custom interface for making this picture of 46 people. It seems like the kind of thing that we can solve.”
Parker-Holder: Genie 3 is an environment simulator, not an autonomous agent
“We designed it to be an environment rather than an agent, right? So Genie three is very much like an environment model. Like we don't see it as like an agent itself that can like think and act in the world. It's more just a general purpose sort of simulator in…”
Parker-Holder: DeepMind kept Veo 3 and Genie 3 as separate projects
“We obviously made a choice that we want VO three and Gini three to be separate projects this year, right?”
Parker-Holder: Genie 3 outputs look real to non-expert viewers
“And it, it's at the point where, like, a human who is not an expert, like, will watch it and think it looks real, right?”
Chen: Google DeepMind cut data center power use by 20 to 25%
“All of these variables fed into a system, and they were able to take 20 to 25% of the electricity out of the equation, serving the exact same workload.”
Brichtova: DeepMind prototyped physical chair designed via fine-tuned model
“We just worked with Russ Lovegrove on fine tuning a model on his sketches so that he can then create something new out of that, and then we design an actual physical chair that we, like, have a prototype of.”
Oliver Wang: Nano Banana exceeded initial LMSYS Chatbot Arena query capacity
“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.”
Brichtova: Nano Banana text rendering underperformed at initial release
“For this first release, the model's not as good as text rendering at, as we would like it to be, and that's something that we want to fix in the future”
Oliver Wang: Nano Banana renders functional webpages from HTML code images
“I've seen examples where people give it, like an image of HTML code and have the model render the webpage.”
Wang: Nano Banana follows instructions less effectively in long conversations
“Once you get into real long conversations, like it starts to follow your instructions a little bit worse”
Parker-Holder: Genie 2 suffered transfer issues from image prompting
“So I think that that's actually a really important capability that we didn't have with Genie too as well, right? Because we relied on image prompting. And so, there was some transfer issue, like, where you rely on imagine to generate the image, and that often …”
Fruchter: DeepMind achieved real-time interactive environment generation
“We weren't sure, like, how, how big it's gonna be but we definitely felt, I felt definitely that we have something that was kind of like for a long time coming, basically being able to generate environments in real time. I think a lot of work that was done in,…”
Fruchter: Genie 3 currently caps spatial memory retention at one minute
“There was not like, there is no like fundamental limitation, but Currently the current design we limited to one minute of this type of memories.”
Parker-Holder: Veo 2 launched one week after Genie 2
“So we had this Genie II project that was much more sort of like, three environments that it could generate, and it wasn't super high quality. It felt like it coming from Genie I, but it wasn't the same quality as things like VO II, which you know, the Saints o…”