Claude Code Security
Claude Code Security, a new capability built into Claude Code on the web, is now available in a limited research preview. It scans codebases for security vulnerabilities and suggests targeted software patches for human review.
15 deployments dated February 16 to 22, 2026 are in The Deploy Log: 3 leads, 3 in Models and APIs and 9 in Tools and products, from 4 publishers. They include Claude Code Security from Anthropic, Claude Sonnet 4.6 from Anthropic, Gemini 3.1 Pro from Google DeepMind, GGML and llama.cpp join HF from Hugging Face, Lyria 3 music generation from Google DeepMind and 10 others. Every item sourced to the publisher's own page.
Claude Code Security, a new capability built into Claude Code on the web, is now available in a limited research preview. It scans codebases for security vulnerabilities and suggests targeted software patches for human review.
Claude Sonnet 4.6 is a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. Pricing remains the same as Sonnet 4.5, starting at $3/$15 per million tokens, with a 1M token context window in beta.
Gemini 3.1 Pro is rolling out in preview via the Gemini API in Google AI Studio, Gemini CLI, Google Antigravity, Android Studio, Vertex AI, Gemini Enterprise, the Gemini app, and NotebookLM. On ARC-AGI-2 it achieved a verified score of 77.1%, more than double the reasoning performance of 3 Pro.
GGML, creators of llama.cpp, are joining Hugging Face, with Georgi Gerganov and team dedicating 100% of their time maintaining llama.cpp with full autonomy and leadership on technical directions and the community.
Lyria 3, Google DeepMind's latest generative music model, is rolling out in beta in the Gemini app, letting anyone make 30-second tracks from text or images with custom cover art generated by Nano Banana.
Unsloth and Hugging Face Jobs enable fast LLM fine-tuning of LiquidAI/LFM2.5-1.2B-Instruct through coding agents like Claude Code and Codex, with Unsloth providing approximately 2x faster training and about 60% less VRAM usage compared to standard methods.
AI Gateway now supports video generation through AI SDK 6, with four initial video models and 17 variations covering text-to-video, image-to-video, first and last frame, and reference-to-video generation types.
Vercel now supports programmatic access to billing usage and cost data through the API and CLI, with the new /billing/charges endpoint returning data in the FOCUS v1.3 open-standard format.
Gradio 6 shipped gr.HTML with custom templates, scoped CSS, and JavaScript interactivity, letting Claude or any other frontier LLM generate frontend, backend, and state management in a single Python file with no build step.
Recraft V4 is now available on AI Gateway, a text-to-image model built for professional design and marketing use cases with improvements in photorealism, realistic skin, natural textures, and fewer synthetic artifacts.
The Runtime Logs search bar in the project dashboard has been redesigned with structured filters that parse level:error or status:500 into visual pills, smarter suggestions based on actual log data, and automatic conversion of pasted Vercel Request IDs into filters.
Skills on skills.sh now have automated security audits from partners Gen, Socket, and Snyk, allowing rapid scaling to audit over 60,000 skills and counting.
Streamdown 2.3 ships with a fully cleared bug backlog, applying a unified nested-card design to tables, code blocks, and Mermaid diagrams, with sticky action buttons and plain text code blocks that render immediately.
Runtime Logs exports now stream directly to the browser, with all plans able to export up to 10,000 requests per export and Observability Plus subscribers able to export up to 100,000 requests.
Gemini 3.1 Pro Preview is now available on AI Gateway, bringing quality improvements across software engineering and agentic workflows with more efficient thinking.
The edition every row came from arrives in your inbox, free.
Join free