Sbayer·1d agoDo AI Models Perceive The Same Concepts From Text Representation Learning Compared to Vision…A great thought experiment to help me understand “The Platonic Representation Hypothesis” which suggests that models trained on different…
Ravi Sankar Uppala·Oct 23Should AI Think in Words?Latent-space reasoning may matter even more than latent AI-to-AI communication, because it changes the substrate a single model uses to…
Aditya Inamdar·Oct 19HybridAgent: The Agent That Thinks in Latent Space and Acts Through TextEvery agent you have used thinks by writing tokens. Every thought costs money, fills your context window, and lands in your logs. A…
Saddek Belaid·Oct 16Can We Steer How AI Transforms Meaning?Toward a Governable Geometry for Measuring and Steering Semantic Transformations in Generative AI
InAI-ML Interview PlaybookbySajid Khan·Oct 9Let’s Break Down Stable DiffusionHow AI Turns Random Noise Into Stunning ImagesA response icon1A response icon1
Yogesh Malik·Oct 6The Immobile Embryo: The Dark Cost of Living by ProxyThe Interface Between You and the World — A button gives you control over a machine, but surrenders your control over yourself.
Fredric Cliver·Oct 4Memory Is Not a DocumentBeyond Descriptive Context: Towards Integrated Context for High-Context AgentsA response icon1A response icon1
InAI Advances BriefsbySijuade Oguntayo·Oct 1My Best Driving World Model Agent Was the Worst DriverReward shaping lessons from DreamerV3 in a simulated city, and what I only found by watching itA response icon2A response icon2
Markys Gariboldo·Sep 27McGreggors as a Subject of Network Relations: The Ontological Transition from Utilitarian Algorithm…0. The Ontological Crisis
InTowards AIbyJAIGANESAN·Sep 22LatentMoE: NVIDIA’s Latent Mixture of Experts Explained Through Equations, Architecture, Code and…From the dense layer, to the mixture of experts, to the latent space the experts moved into, and the two byte counts that explain whyA response icon3A response icon3
