Anthropic's Claude Opus 5 and Sonnet 5 reject any non-default value for temperature, top_p, or top_k with a 400 error, a behavior in place since Opus 4.7, replacing the sampling parameter with output_…
Anthropic's Claude Code now supports dynamic workflows that replace the context-window ceiling with a JavaScript-based orchestration script, spawning up to 64 subagents per task. Jarred Sumner, creato…
Anthropic's Claude Code tool can be run in two modes: interactive REPL for exploratory tasks requiring human judgment, and non-interactive -p mode for scripting and CI pipelines. The -p mode with --ba…
Google shut down Gemini CLI on June 18, 2026, replacing it with Antigravity CLI, causing individual-tier users to receive HTTP 410 errors and breaking scripts, CI pipelines, and automation. Enterprise…
Anthropic's Claude Sonnet 5 offers a 1-million-token context window at standard pricing with no long-context tax, but the cost of filling it remains significant. Whole-repo Q&A with caching costs abou…
Anthropic, AWS Bedrock, and OpenRouter all offer the same Claude models at identical per-token prices, but differ in billing, freshness, and operational features. AWS Bedrock is best for committed AWS…
Anthropic's Claude Code tool has been automatically appending session URLs to commits and pull request descriptions since version 2.1.179, exposing internal links in public git history. The company re…
Mixture-of-Experts (MoE) models like Qwen3-30B-A3B and DeepSeek-V3 separate total parameters (memory) from active parameters (compute), allowing a 30B-parameter model to run at the speed of a 3B model…
Cursor and Anthropic have introduced middle-tier safety modes for AI coding agents, replacing the binary choice between constant approval prompts and unrestricted execution. Cursor's Auto-review, ship…
A comparison of four terminal coding agents in 2026—goose, Claude Code, OpenCode, and Pi—finds that frontier models have largely converged, making the harness around them the key differentiator. Claud…
Anthropic added --safe-mode to Claude Code v2.1.169 to help users isolate whether a customization layer—such as CLAUDE.md rules, hooks, skills, plugins, or MCP servers—is causing broken behavior. Runn…
Anthropic paused a planned billing change for its Claude Agent SDK on June 15, which would have separated programmatic usage from subscription pools and charged API rates. The change would have ended …
Anthropic shipped dynamic workflows to general availability in late May, allowing Claude Code to write JavaScript orchestration scripts that fan out parallel subagents and check its own work. The feat…
Anthropic shipped two first-party schedulers in spring 2026: Claude Code Routines (April research preview) and Managed Agents scheduled deployments (June public beta), both allowing recurring agent wo…
The U.S. Commerce Department ordered Anthropic to take its Claude Fable 5 and Mythos 5 AI models offline on June 9, citing a claimed jailbreak that allows foreign nationals to exploit code vulnerabili…