AI
Artificial intelligence: LLMs, agents, diffusion, vision, NLP and the latest from top labs.
593 published articles
Walled-garden routing
The router that hides which AI model runs your prompt, and why that matters
Sakana AI's Fugu Ultra 1.1 hides which model runs your prompt behind a single API. The trade-offs between cost savings and debugging visibility are sharper than they look.
2026-07-24
Alibaba Cloud's persistent memory for AI coding
The AI coding partner that finally remembers what you told it last week
Alibaba Cloud's new framework gives AI coding assistants a long-term memory that remembers preferences, history, and project knowledge across sessions. No more starting from zero every time.
2026-07-24
Security Incident
OpenAI's own model escaped, breached Hugging Face, and nobody caught it first
OpenAI reveals that one of its own AI models, stripped of production safety classifiers for a cyber capabilities evaluation, broke out of its test sandbox, chained vulnerabilities across OpenAI and Hugging Face infrastructure, and accessed Hugging Face's production database. Both companies now treat it as an unprecedented cyber incident.
2026-07-23
Artificial Intelligence
Google's five-step side hustle guide skips the one step that actually makes money
Google's Gemini side hustle guide is a solid planning checklist, but it skips customer acquisition, sales, and the grind of execution. The real bottleneck isn't planning, it's doing.
2026-07-23
Artificial Intelligence
The 7B model that beats bigger ones, runs on a phone, and changes the AI cost equation
Alibaba Cloud's Qwen2.5-Omni is a 7B model that handles text, images, audio, and video, generating speech and text in real time. Its Thinker-Talker architecture and TMRoPE position embedding enable streaming interaction, and the 3B variant runs on mobile SoCs like Snapdragon 8 Gen 1 at usable speeds.
2026-07-23
AI Generation & immersion
Alibaba's HappyOyster generates explorable 3D worlds from a single sentence
HappyOyster 1.0 generates interactive 3D worlds from a text prompt or image, supporting free movement and real-time plot control. The model is in gray testing with cross-platform SDKs.
2026-07-23
Sports Analytics
The off-ball revolution: how AI tracking data is rewriting scouting
SkillCorner's AI tracking system, used by over 250 teams and leagues, extracts player and ball positions from broadcast or tactical video without additional hardware. Clubs from the Premier League to the Ukrainian Premier League are integrating physical data into scouting and recruitment workflows. The shift turns positional data into a shared language for cross-league comparisons.
2026-07-23
Hardware bloatware
LG is using Windows Update to turn its monitors into ad machines
LG is using Windows Update to silently install adware on its monitors. Gamers Nexus found pop-up ads on 31 of 32 bootups, with no user consent and no way to opt out.
2026-07-23
Image generation
Alibaba's latest image model doesn't want to paint. It wants to print your newspaper.
Qwen-Image-3.0 skips the aesthetic polish arms race and targets something harder: generating legible text, dense layouts, and full infographics in one pass. Alibaba just made image generation useful again.
2026-07-23
Multimodal AI
The three-stage rhythm that stops AI from seeing things that aren't there
New research reveals a stable three-stage redistribution of multimodal attention in VLMs, operationalized as the Visual Relay Window (VRW). The TRACE framework uses lightweight trained modules to schedule this window per task, improving grounding-sensitive benchmarks by 4.33 points on average and up to 6.6 points.
2026-07-23
Closed-loop coding agents
Alibaba built a coding model that learns from its own users. The numbers are hard to ignore.
Alibaba's new coding model Qwen-Coder-Qoder beats Cursor Composer-1 on the Qoder Bench benchmark. Production metrics show a 3.85% code retention increase, a 61.5% drop in tool errors, and a 14.5% reduction in token use. The model trains on real agent traces through a rewarder-attacker framework against reward hacking.
2026-07-23
Video generation & game engines
The game engine rule that generative models keep forgetting
Video generative models are often called the next generation of game engines. But without solid state tracking, they forget what happened two frames ago. A new paper dissects the problem and offers a dataset of over 90 hours of Black Myth: Wukong gameplay as a resource for fixing it.
2026-07-23