I think you're overstating the distinction between ML and generation - plenty of ML methods involve generative models. Even basic linear regression with a squared loss can also be framed as a generative model derived by assuming Gaussian noise. Probabilistic PCA, HMMs, GMMs etc... generation has been a core part of ML for over 20 years.
There is a lot of overlap between AI and Neuroscience, especially among older researchers. For example Karpathy's PhD supervisor, Fei-Fei Li, researched vision in cat brains before working on computer vision, Demis Hassabis did his PhD in Computational Neuroscience, Geoff Hinton studied Psychology etc... There's even the Reinforcement Learning and Decision Making conference (RLDM - very cool!), which pairs Reinforcement Learning with neuro research and brings together people from both disciplines.
I suspect the average AI researcher knows much more about the brain than typical CS students, even if they may not have sufficient background to conduct research.
Their recent paper suggests the active user base is continuing to grow consistently with consistent/growing usage based on how long they've been using the app.
To encourage more usage, wouldn’t it be in their best interest to write about all the different ways you can use it by claiming these are the ways people are using it?
Gemini 2.5-Pro was great when it released, but o3 and GPT-5 both eclipsed it for me—the tool use/search improvements open up so many use cases that Gemini fails at.
I doubt this is coming from RLHF - tweets from the lead researcher state that this result flows from a research breakthrough which enables RLVR on less verifiable domains.
Math RLHF already has verifiable ground truth/right vs wrong, so I don't what this distinction really shows.
And AI changes so quickly that there is a breakthrough every week.
Call my cynical, but I think this is an RLHF/RLVR push in a narrow area--IMO was chosen as a target and they hired specifically to beat this "artificial" target.
Have you tried the Canvas feature for collaborative writing? Agreed on voice mode - would be great to be able to narrate while doing busywork round the house.
As I understand, Canvas belongs to the chat and no to the project. If there was a way to link Canvas/artifact to the project - that would do the trick.
I don't know what price you'd pay in your hypothetical scenario, but I would say that European universities often take a larger chunk of equity than US unis where spinouts are concerned [1]. Most US universities take between 0-5% equity, where EU could go to 10%, and UK unis up to 20-30%.
the feeling that they needed to include a few paragraphs of “look this isn’t the single digit amounts your friends are getting… but… it’s dilutive and we know best for you” language is telling
Exactly. A lot of academics fall for it, thinking these are normal amounts. Then later when they try to raise money they often get into trouble as no invester in their right mind wang to touch them. Having a university as a major share holder with voting seats isn't a great idea!
If we're talking about existing EU funding mechanisms, the participating universities take no equity in their startup partners whatsoever, they just get paid part of the funding pot to do a bit of related research and publish it, and might be able to generate a bit of their own IP
The technical report does go into a lot of depth about how they use RL, such as the modified GRPO objective they use. As far as the README, I imagine most people active in the field understand the implications of "RL" for a reasoning model.
