Thanks for the clarification. This is indeed where I saw all those models listed, including the ~ 400 GB R1 671B, which made me think that it could potentially fit into the 512 GB of unified memory on a Mac Studio.
TECHNOLOGY
-
Proto Hologram’s Revolutionary Technology Transforms Video Communication
By
–
La tecnología de Proto Hologram es realmente sorprendente y tiene el potencial de revolucionar las videollamadas, incluso en formato table top.
— Juan Merodio (@juanmerodio) 3 juin 2025
Estamos ante el futuro que nos permitirá conectarnos de forma más realista y cercana con otras personas? pic.twitter.com/07xJwojnRnProto Hologram's technology is truly astonishing and has the potential to revolutionize video calls, even in tabletop format. Are we facing the future that will allow us to connect in a more realistic and intimate way with other people?
-
High-Entropy Tokens Drive LLM Reasoning in RLVR
By
–
It turns out you can drop 80% lowest-entropy tokens and still get good performance. This paper shows that only ~20% of tokens—those with the highest entropy—actually drive the reasoning process in LLMs trained with Reinforcement Learning with Verifiable Rewards (RLVR). The rest?
-
AI Capabilities Sufficient for Transformative 10-20 Year Impact
By
–
And yeah if capabilities stop ~now or at 20% more than now that's already sufficient to be fairly transformative after 10-20 years to digest and put them in everything, much like it took a while to retool and put the Internet in everything, and see second and third order effects.
-
AlphaOne: Modulated Reasoning Optimizes LRM Performance
By
–
Large Reasoning Models (LRMs) often struggle to balance deep thinking with efficient generation. Prior methods use monotonic scaling (e.g. "more steps = better results") but lack flexibility. Enter AlphaOne: Modulated Reasoning at Test Time AlphaOne introduces a universal
-
AI Factory Flywheel Breakthroughs Unveiled at COMPUTEX 2025
By
–
Experience the momentum from our #COMPUTEX2025 keynote and #GTCTaipei where we showcased breakthroughs driving the AI factory flywheel. From major announcements to hands-on demos and workshops, see how we're delivering full-stack AI infrastructure for the next industrial
-
Stephen Wolfram’s Intelligence Exceeds the Ruliad Concept
By
–
Stephen may be the only person with a brain bigger than the Ruliad
-
Fast Web Renderer for 3D Gaussian Splats Released Open Source
By
–
Check out this shiny new, fast and dynamic web renderer for 3D Gaussian Splats! The things one could do are just mind boggling! So proud of the @theworldlabs team that made this happen, and we are making this open source for everyone! https://t.co/RVwKViGJFc
— Fei-Fei Li (@drfeifei) 2 juin 2025Check out this shiny new, fast and dynamic web renderer for 3D Gaussian Splats! The things one could do are just mind boggling! So proud of the @theworldlabs team that made this happen, and we are making this open source for everyone!
-
Tracking AI capability predictions for future assessment
By
–
n.b. Almost every time I publicly describe discrete capabilities like these a thought I have is "I want to remember in the future what I previously thought about the future shape of the curve to know if I need to update radically more than I have updated."