Search for a command to run...
Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
Track DeepSeek V4's pricing against incumbent frontier models — at $0.14/M input for Flash and $1.74/M for Pro, it sets a new low-cost reference point that could pressure pricing across the entire API market.
Developers can access GPT-5.5 today — before its official API launch — by installing the `llm-openai-via-codex` plugin and routing prompts through their existing Codex subscription, with OpenAI's explicit blessing.
Developers running local LLMs can now access a model that claims flagship-level agentic coding performance in a 16.8GB quantized package, runnable on consumer hardware via `llama.cpp`.
Developers relying on Copilot's individual plans for agentic coding workflows should review the new token-based limits and Pro+ tier requirements before their access to models like Claude Opus 4.7 is affected.
Developers evaluating image generation APIs should note that `gpt-image-2`'s quality gains are most apparent at maximum resolution settings, but those settings carry meaningful per-image costs that need to be factored into production budgets.
Developers and educators building workflows or curricula around Claude Code should monitor Anthropic's pricing decisions closely, as even a quickly-reversed test change signals potential future access restrictions that could affect tool choices and teaching materials.
Developers budgeting for Claude Opus 4.7 should account for up to ~40% higher costs on text workloads due to tokenizer inflation, and should test their specific content types — PDFs, images, and raw text behave very differently — using the updated token counter tool before migrating from Opus 4.6.
Developers using Datasette as a data backend can now choose the right Google Sheets integration pattern based on whether their instance requires API token authentication.
Developers and practitioners building on Claude can use this diff to understand exactly how Anthropic is shaping model behavior — including new tool-discovery mechanics via `tool_search`, stricter safety escalation rules, and reduced verbosity defaults — which directly affects how Claude-powered agents will respond in production.
Researchers and practitioners tracking Claude's behavior over time can use this git-based structure to precisely diff system prompt changes between model versions without manual parsing.