Open-Source AI
Open models — Llama, Mistral, DeepSeek, Qwen and others — are catching up to closed labs and let you run AI on your own hardware, vendor-free. That shifts the balance of power, the safety debate and the economics of the field. Here is everything on open-source AI: open-weight releases, licenses, local deployment and the race against closed models.
TopoGPU Computes Persistent Homology 53x Faster on Average
The authors released TopoGPU, a streaming GPU pipeline for image persistent homology: 53.24x faster than Cubical Ripser on average, and up to 198.01x faster at best.
DOGS Beats 9 Baseline Methods at Logo Generation Across Two Renderers
DOGS drops prompt rewriting: a GFlowNet samples a logo design graph and penalizes similarity to existing marks. The authors compared it with nine baseline methods.
Kolmogorov-Arnold Networks Match MLP Performance With 40% Fewer Samples
In reinforcement learning, KANs reach the same results as MLPs with 40% fewer samples. Peak relative gain is up to 50%, and reward noise does not erase the…
Epoch AI Releases Digest: AI Prices Plummet, Billions of Agents Coming
NVIDIA Dynamo: Session-Based Infrastructure Management for Agentic Inference
A Non-Programmer Used Claude Code to Rebuild an English-Learning App With a Server and Offline Mode
Amazon finishes 1,000th Leo satellite, internet launch weeks away
Apple names Steve Smith head of M&A and moves Adrian Perica to services
Under new CEO John Ternus, Apple is changing its M&A chief: Steve Smith replaces Adrian Perica, who moves to services. AI deals now wait on the new head.
Station F and Anthropic: the AI boom is bringing startups back offline
Roxanne Varza (Station F) and Aiden Blake (Anthropic) explained at a conference in Turin why the AI boom is pulling startups back offline. Station F launched its…
Dealroom CEO: Europe's first trillion-dollar startup may already exist
Shengshu releases Vidu Q4 Preview, aiming for a "DeepSeek moment" for video
GitHub Now Counts Draft Pull Requests Toward Open PR Limits
Wasserstein BaryBooster Turns Diffusion Realism into Event Forecasting Accuracy
Google, China, and the British AI institute: how models are learning to break down, hack, and jam
Three studies showed where frontier AI is heading: Google's models break down under pressure, cyber agents are advancing quickly, and China is training AI for…
A way to sync sessions between a PC and laptop is now available for OpenAI Codex
OpenAI Codex has no built-in synchronization between devices, so a CLI tool called codexSync has appeared to transfer sessions, context, and history between a PC…