AI

Physical AI

Alibaba's Qwen is now the brain inside 150,000 robots, cars, glasses, and drones

Alibaba's Qwen AI family now powers over 150,000 hardware devices, from humanoid robots to children's cameras, as the company pivots from chatbots to Physical AI, integrating multimodal models into robots, cars, glasses, and drones.

2026-07-14

Cloud strategy

Alibaba's AI bet: lock in the enterprise before the model race is over

Alibaba is betting the second half of 2026 on an integrated AI stack, not a single flagship model. Its strategy is to lock enterprises into its cloud via interoperable infrastructure, from agentic O&M to data warehousing, rather than to win benchmark titles.

2026-07-14

Codex just became the ChatGPT desktop app, not a separate tool

OpenAI folded Codex into the ChatGPT desktop app on macOS and Windows, adding inline code editing, GitHub PR reviews, multi-repo support, and faster Computer Use mode via GPT-5.6.

2026-07-14

Artificial Intelligence

An AI tutor just hit 1.3 SD in a real college class. Educational research hasn't seen this in decades.

A new AI tutor tested at Dartmouth College achieved an effect size of up to 1.30 standard deviations in a real course, well above typical educational interventions. The results suggest AI can now deliver personalized tutoring at scale, but questions about generalizability, economics, and long-term retention remain.

2026-07-14

Enterprise AI coding

Gartner says Cursor is leading enterprise AI coding. Here's what that actually means.

Gartner named Cursor a Leader in its first-ever Magic Quadrant for enterprise AI coding agents, with the top score on Completeness of Vision. This dossier unpacks what that placement actually measures, what the 70% of Fortune 500 stat leaves out, and the eighteen months of product decisions that got Cursor there.

2026-07-14

AI Development

Vibe coding is fast. Shipping what it builds is where the real work begins.

Vibe coding accelerates prototyping and lowers the barrier for beginners, but its hidden technical debt, security risks, and lack of reasoning traceability challenge assumptions that AI-generated code is ready for production. Developers must weigh speed against control.

2026-07-14

LLM Performance

A Chinese video-generation startup just quietly beat Claude Opus at coding

MiniMax's M2.7 scores 56.22% on SWE-Pro, matching near-Claude Opus performance, while touting 97% skill adherence on complex tasks and superior office productivity editing. The model signals a shift from benchmark chasing to real-world agent deployment.

2026-07-14

Artificial intelligence

Sonnet 4.6 just made Opus look expensive. That changes everything.

Anthropic's Claude Sonnet 4.6 matches or beats Opus-class performance on key benchmarks while keeping the same pricing as Sonnet 4.5. Early developer preference data and customer testimonials suggest the model is already displacing costlier alternatives for real-world agentic and coding tasks.

2026-07-14

AI Infrastructure

Ollama's 85 percent stat means exactly what you think it means

Ollama's $88 million raise leads with an 85%-of-Fortune-500 stat that sounds like saturation and proves almost nothing. An analysis of why this specific move has become the default opening line of AI infrastructure funding announcements, and what's actually driving the real money into open-weight inference.

2026-07-14

File over config

Vercel's Eve 0.22 wants your AI agents to live as files on disk, not secrets in a config

Vercel's Eve 0.22.6 brings a filesystem-based structure to AI agent development: instructions, tools, skills, and integrations all live as inspectable files, with multi-model support, human-in-the-loop prompts, and subagent orchestration.

2026-07-14

Funding round

Ollama's $88 million bet that open-weight models will do what Docker did for containers

Ollama raised $88 million to make open-weight models the default way to run inference, betting the Docker playbook works for AI. Investors include Benchmark, Theory Ventures, 8VC, and Y Combinator.

2026-07-14

Orchestrator swap

Perplexity swapped its orchestrator model and the cost-performance chart is brutal

Perplexity swapped Grok 4.5 into Computer as its orchestrator model, claiming top accuracy on its internal benchmark at roughly half the cost of Claude Opus 4.8. The move signals a broader shift: which model you pair with an agent matters as much as the model itself.

2026-07-14