Moonshot AI, maker of the Kimi models, is aiming for $2 billion in annual revenue, with OpenRouter data showing up to 300 billion tokens generated daily by K3 models despite a slight usage decline.
An AWS blog post argues that price per token misses what production workloads pay for, and introduces an open-source harness to benchmark OpenAI models on Amazon Bedrock by outcomes.
AWS explains how to build and deploy MCP Apps with interactive HTML widgets on Amazon Bedrock AgentCore, using a host-agnostic standard that works across compatible AI hosts.
The week's 10 most important AI developments in one place, with links to our full sourced briefs.
OpenAI details how its Habitat storage system grew from a Python library into a globally distributed platform supporting 1 billion ChatGPT users and 22 million requests per second.
NVIDIA's GeForce NOW cloud gaming service adds nine new titles this week, including WARDOGS at early-access launch, a Valheim 1.0 update, and Bus Simulator 27.
A second mathematician has publicly challenged OpenAI over the origins of the data behind its mathematical results, alleging dishonesty and a lack of transparency.
A July 2026 transmission line fault in Ashburn, Virginia dropped more than 3 gigawatts of data center load in seconds, echoing an earlier incident and pointing to grid architecture challenges for AI infrastructure.
This piece discusses the rebuilding of AUTOMATIC1111 using Gradio Workflow to enhance development processes.
GitHub Copilot brought AI code completion to millions of developers inside their editors. Here is what it does well, where it needs supervision, and how it fits a modern workflow.
Cursor rethinks the code editor around AI rather than bolting AI onto one. With codebase-aware chat and multi-file edits, it pushed the 'AI-native IDE' idea into the mainstream.
Transformers is the open-source Python library that made state-of-the-art AI models accessible to everyone. Here is what it does, who should use it, and where it fits in a modern AI stack.
Stable Diffusion made high-quality text-to-image generation open and runnable on consumer GPUs, sparking a vast ecosystem of tools and fine-tunes. Here is what it is and why it mattered.
Before GPT dominated headlines, BERT showed that pretraining a Transformer to read text in both directions could transform language understanding. Here is what the landmark 2018 paper introduced.
The 2020 GPT-3 paper made a startling claim: make a language model big enough and it learns new tasks from a few examples in the prompt, with no retraining. Here is what it showed.
CLIP learned to link pictures and language by studying hundreds of millions of image–caption pairs from the web. It quietly became the foundation for image search and generation.
Every modern language model — GPT, Claude, Gemini, Llama — descends from one 2017 paper. Here is what 'Attention Is All You Need' actually proposed, in plain English, and why it changed everything.