Claudenotes Brief

A new project purge command wipes per-project state, the model picker now reads from your gateway, and OAuth login finally works in WSL2 and SSH. Plus Pentagon AI deals without Anthropic, Mythos scrutiny, and a $900 billion valuation in the works. In this episode: (00:00) Introduction (00:45) Claude Code Updates (02:59) Under the Hood (04:28) In the News Further reading: - Lessons from building Claude Code: Prompt caching is everything (Anthropic Engineering): https://claude.com/blog/lessons-from-building-claude-code-prompt-caching-is-everything - Onboarding Claude Code like a new developer: Lessons from 17 years of development (Anthropic Engineering): https://claude.com/blog/onboarding-claude-code-like-a-new-developer-lessons-from-17-years-of-development - Pentagon Makes Deals With A.I. Companies to Expand Classified Work (New York Times): https://www.nytimes.com/2026/05/01/us/politics/pentagon-ai-companies-deals.html - Why Anthropic's Mythos Is Sparking Global Alarm (Bloomberg): https://www.bloomberg.com/news/articles/2026-04-30/mythos-why-anthropic-s-ai-model-is-sparking-global-alarm - Anthropic Weighs Funding Offers at Over $900 Billion Valuation (Bloomberg): https://www.bloomberg.com/news/articles/2026-04-29/anthropic-considering-funding-offers-at-over-900-billion-value - Claude-powered AI agent's confession after deleting a firm's entire database (The Guardian): https://www.theguardian.com/technology/2026/apr/29/claude-ai-deletes-firm-database Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Config settings now persist across restarts, vim mode picks up visual selection, and the Opus 4.7 context window math gets corrected. Plus Google commits up to forty billion dollars to Anthropic, and Mozilla used Mythos to fix 271 Firefox bugs. In this episode: (00:00) Introduction (00:45) Claude Code Updates (02:33) Under the Hood (03:43) In the News Further reading: - Building agents that reach production systems with MCP (Anthropic Engineering): https://claude.com/blog/building-agents-that-reach-production-systems-with-mcp - Built-in memory for Claude Managed Agents (Anthropic Engineering): https://claude.com/blog/claude-managed-agents-memory - Anthropic Probes Possible Unauthorized Access to Mythos AI Model (Wall Street Journal): https://www.wsj.com/tech/ai/anthropic-probes-possible-unauthorized-access-to-mythos-ai-model-3da1ee20 - Google Commits to Invest Up to $40 Billion in Anthropic (New York Times): https://www.nytimes.com/2026/04/24/technology/google-anthropic-investment-artificial-intelligence.html - Mozilla Used Anthropic's Mythos to Find and Fix 271 Bugs in Firefox (Wired): https://www.wired.com/story/mozilla-used-anthropics-mythos-to-find-271-bugs-in-firefox/ - Microsoft to integrate Anthropic's Mythos into its security development program (Reuters): https://www.reuters.com/technology/microsoft-integrate-anthropics-mythos-into-its-security-development-program-2026-04-22/ Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Claude Opus 4.7 is now available in Claude Code with a new extra-high effort level and an interactive slider for tuning the speed-intelligence tradeoff. This week also brought a native binary for faster startup, a parallel multi-agent code review command, and significant security hardening for Bash permission rules. In this episode: (00:00) Introduction (00:45) Claude Code Updates (03:05) Under the Hood (04:20) In the News Further reading: - Best practices for using Claude Opus 4.7 with Claude Code (Anthropic Engineering): https://claude.com/blog/best-practices-for-using-claude-opus-4-7-with-claude-code - Using Claude Code: session management and 1M context (Anthropic Engineering): https://claude.com/blog/using-claude-code-session-management-and-1m-context - Introducing routines in Claude Code (Anthropic Engineering): https://claude.com/blog/introducing-routines-in-claude-code - White House and Anthropic Hold 'Productive' Meeting, Aiming for a Compromise (New York Times): https://www.nytimes.com/2026/04/17/technology/white-house-anthropic-artificial-intelligence.html - Anthropic Attracts Investor Offers at an $800 Billion Valuation (Bloomberg): https://www.bloomberg.com/news/articles/2026-04-14/anthropic-attracts-investor-offers-at-a-800-billion-valuation - Uber CTO Shows How Claude Code Can Blow Up AI Budgets (The Information): https://www.theinformation.com/newsletters/applied-ai/uber-cto-shows-claude-code-can-blow-ai-budgets - Anthropic Changes Pricing to Bill Firms Based on AI Use as Demand Jumps (The Information): https://www.theinformation.com/articles/anthropic-changes-pricing-bill-firms-based-ai-use-amid-compute-crunch Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Claude Code's default effort level shifts from medium to high for most users, meaning better output quality at the cost of more tokens. Critical security patches fix a Bash permission bypass and command injection vulnerabilities. Plus, Mythos's cybersecurity implications draw attention from Wired, the New York Times, and federal regulators. In this episode: (00:00) Introduction (00:45) Claude Code Updates (02:49) Under the Hood (04:10) In the News Further reading: - Seeing like an agent: how we design tools in Claude Code (Anthropic Engineering): https://claude.com/blog/seeing-like-an-agent - How and when to use subagents in Claude Code (Anthropic Engineering): https://claude.com/blog/subagents-in-claude-code - Claude Managed Agents: get to production 10x faster (Anthropic Engineering): https://claude.com/blog/claude-managed-agents - Anthropic's Mythos Will Force a Cybersecurity Reckoning—Just Not the One You Think (Wired): https://www.wired.com/story/anthropics-mythos-will-force-a-cybersecurity-reckoning-just-not-the-one-you-think/ - Banks Are Warned About Anthropic's New, Powerful A.I. Technology (New York Times): https://www.nytimes.com/2026/04/10/business/anthropic-claude-mythos-preview-banks.html - Anthropic Agrees to Rent CoreWeave AI Capacity to Power Claude (Bloomberg): https://www.bloomberg.com/news/articles/2026-04-10/anthropic-agrees-to-rent-coreweave-ai-capacity-to-power-claude - Anthropic's New Product Aims to Handle the Hard Part of Building AI Agents (Wired): https://www.wired.com/story/anthropic-launches-claude-managed-agents/ Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Claude Code ships an interactive Bedrock setup wizard and per-model cost breakdowns. Anthropic scrambles to contain a source code leak after hackers repackage it with malware, and the BBC reports on growing frustration with usage limits. In this episode: (00:00) Introduction (00:45) Claude Code Updates (02:53) Under the Hood (03:54) In the News Further reading: - Anthropic Races to Contain Leak of Code Behind Claude AI Agent (Wall Street Journal): https://www.wsj.com/tech/ai/anthropic-races-to-contain-leak-of-code-behind-claude-ai-agent-4bc5acc7 - Security News This Week: Hackers Are Posting the Claude Code Leak With Bonus Malware (Wired): https://www.wired.com/story/security-news-this-week-hackers-are-posting-the-claude-code-leak-with-bonus-malware/ - Cursor Launches a New AI Agent Experience to Take On Claude Code and Codex (Wired): https://www.wired.com/story/cusor-launches-coding-agent-openai-anthropic/ - Claude Code users hitting usage limits 'way faster than expected' (BBC News): https://www.bbc.com/news/articles/ce8l2q5yq51o - Harnessing Claude's intelligence (Claude Blog): https://claude.com/blog/harnessing-claudes-intelligence - Quantifying infrastructure noise in agentic coding evals (Anthropic Engineering): https://www.anthropic.com/engineering/infrastructure-noise Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Auto mode brings safer permissionless operation to Claude Code with built-in safety heuristics. This week also delivers transcript search, conditional hook filters, and a native PowerShell preview on Windows -- alongside news of a federal court ruling preserving Anthropic's government access and reports of an IPO as early as October. In this episode: (00:00) Introduction (00:45) Claude Code Updates (03:13) Under the Hood (04:15) In the News Further reading: - Claude Code auto mode: a safer way to skip permissions (Anthropic Engineering): https://www.anthropic.com/engineering/claude-code-auto-mode - Quantifying infrastructure noise in agentic coding evals (Anthropic Engineering): https://www.anthropic.com/engineering/infrastructure-noise - Anthropic Wins Court Order Pausing Trump Ban on AI Tool (Bloomberg): https://www.bloomberg.com/news/articles/2026-03-26/anthropic-wins-court-order-blocking-trump-ban-on-use-of-ai-tool - Claude AI Maker Anthropic Considers IPO as Soon as October (Bloomberg): https://www.bloomberg.com/news/articles/2026-03-27/claude-ai-maker-anthropic-said-to-weigh-ipo-as-soon-as-october - Anthropic's Claude popularity with paying consumers is skyrocketing (TechCrunch): https://techcrunch.com/2026/03/28/anthropics-claude-popularity-with-paying-consumers-is-skyrocketing/ - Anthropic's Claude Code gets 'safer' auto mode (The Verge): https://www.theverge.com/ai-artificial-intelligence/900201/anthropic-claude-code-auto-mode - PowerShell tool reference (Claude Code Docs): https://code.claude.com/docs/en/tools-reference#powershell-tool Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Claude Code ships a new bare mode that strips it down for scripted pipelines and CI jobs. MCP channels let servers push messages into your session, VS Code gains remote control bridging, and responses now stream line by line. In the news, Anthropic overtakes OpenAI in enterprise revenue and Cursor plans its own rival model. In this episode: (00:00) Introduction (00:45) Claude Code Updates (02:58) Under the Hood (04:03) In the News Further reading: - AI Coding Startup Cursor Plans New Model to Rival Anthropic, OpenAI (Bloomberg): https://www.bloomberg.com/news/articles/2026-03-19/ai-coding-startup-cursor-plans-new-model-to-rival-anthropic-openai - OpenAI to buy Python toolmaker Astral to take on Anthropic (Reuters): https://www.reuters.com/technology/openai-buy-python-toolmaker-astral-take-anthropic-2026-03-19/ - Why Garry Tan's Claude Code setup has gotten so much love, and hate (TechCrunch): https://techcrunch.com/2026/03/17/why-garry-tans-claude-code-setup-has-gotten-so-much-love-and-hate/ - Anthropic turns the tables on OpenAI in critical revenue category (Axios): https://www.axios.com/2026/03/18/ai-enterprise-revenue-anthropic-openai - Product management on the AI exponential (Claude Blog): https://claude.com/blog/product-management-on-the-ai-exponential Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Opus 4.6 now defaults to a one million token context window on Max, Team, and Enterprise plans. MCP servers can prompt you for input mid-task, and a new context diagnostics command flags what's eating your token budget. Plus, Wired profiles OpenAI's race to catch Claude Code, and Anthropic launches a dedicated code review tool. In this episode: (00:00) Introduction (00:45) Claude Code Updates (03:03) Under the Hood (04:10) In the News Further reading: - 1M context is now generally available for Opus 4.6 and Sonnet 4.6 (Claude Blog): https://claude.com/blog/1m-context-ga - Quantifying infrastructure noise in agentic coding evals (Anthropic Engineering): https://www.anthropic.com/engineering/infrastructure-noise - Inside OpenAI's Race to Catch Up to Claude Code (Wired): https://www.wired.com/story/openai-codex-race-claude-code/ - Anthropic seeks appeals court stay of Pentagon supply-chain risk designation (Reuters): https://www.reuters.com/technology/anthropic-seeks-court-stay-pentagon-supply-chain-risk-designation-2026-03-12/ - Microsoft taps Anthropic for Copilot Cowork in push for AI agents (Reuters): https://www.reuters.com/business/microsoft-taps-anthropic-copilot-cowork-push-ai-agents-2026-03-09/ - Anthropic launches code review tool to check flood of AI-generated code (TechCrunch): https://techcrunch.com/2026/03/09/anthropic-launches-code-review-tool-to-check-flood-of-ai-generated-code/ Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Opus 4.6 is now the default model for Max and Team users, and a new loop command lets you schedule recurring prompts inside a session. Plus, voice mode expands to twenty languages, the Pentagon blacklist fallout continues, and Bloomberg reports Anthropic is nearing a twenty billion dollar revenue run rate. In this episode: (00:00) Introduction (00:42) Claude Code Updates (03:12) Under the Hood (04:21) In the News Further reading: - Common workflow patterns for AI agents—and when to use them (Claude Blog): https://claude.com/blog/common-workflow-patterns-for-ai-agents-and-when-to-use-them - Quantifying infrastructure noise in agentic coding evals (Anthropic Engineering): https://www.anthropic.com/engineering/infrastructure-noise - Anthropic courted the Pentagon. Here's why it walked away (Reuters): https://www.reuters.com/technology/anthropic-courted-pentagon-heres-why-it-walked-away-2026-03-04/ - Anthropic's AI Hacked the Firefox Browser. It Found a Lot of Bugs. (Wall Street Journal): https://www.wsj.com/tech/ai/send-us-more-anthropics-claude-sniffs-out-bevy-of-bugs-c6822075 - Amazon says Anthropic's Claude still OK for AWS customers to use outside defense work (CNBC): https://www.cnbc.com/2026/03/06/amazon-aws-anthropic-claude-pentagon-blacklist.html - Anthropic Nears $20 Billion Revenue Run Rate Amid Pentagon Feud (Bloomberg): https://www.bloomberg.com/news/articles/2026-03-03/anthropic-nears-20-billion-revenue-run-rate-amid-pentagon-feud Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

The model picker now shows readable names and flags outdated pinned models. Memory leak fixes target long-running sessions. And the Anthropic-Pentagon contract collapse triggers a federal ban, a lawsuit, and a surge to number one on the App Store. In this episode: (00:00) Introduction (00:42) Claude Code Updates (02:36) Under the Hood (03:36) In the News Further reading: - Quantifying infrastructure noise in agentic coding evals (Anthropic Engineering): https://www.anthropic.com/engineering/infrastructure-noise - How Talks Between Anthropic and the Defense Dept. Fell Apart (New York Times): https://www.nytimes.com/2026/03/01/technology/anthropic-defense-dept-openai-talks.html - Trump has ordered government agencies to stop using Anthropic AI tools (BBC News): https://www.bbc.com/news/articles/cn48jj3y8ezo - Anthropic's Claude hits No. 1 on Apple's top free apps list after Pentagon rejection (CNBC): https://www.cnbc.com/2026/02/28/anthropics-claude-apple-apps.html - What's Really at Stake in the Fight Between Anthropic and the Pentagon (Wall Street Journal): https://www.wsj.com/tech/ai/whats-really-at-stake-in-the-fight-between-anthropic-and-the-pentagon-d450c1a1 - Claude Code settings documentation (Claude Code Docs): https://code.claude.com/docs/en/settings#settings-files Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Claude Sonnet 4.6 arrives with a one million token context window, while Anthropic faces Pentagon disputes and cybersecurity market reactions to Claude Code Security. In this episode: (00:00) Introduction (00:42) Claude Code Updates (02:27) Under the Hood (03:23) In the News Further reading: - Bringing automated preview, review, and merge to Claude Code on desktop (Claude Blog): https://claude.com/blog/preview-review-and-merge-with-claude-code - Increase web search accuracy and efficiency with dynamic filtering (Claude Blog): https://claude.com/blog/improved-web-search-with-dynamic-filtering - The Surprise Hit That Made Anthropic Into an AI Juggernaut (Bloomberg): https://www.bloomberg.com/news/articles/2026-02-20/the-surprise-hit-that-made-anthropic-into-an-ai-juggernaut-mlve4nc2 - Anthropic says new AI model is better at using computers (Bloomberg): https://www.bloomberg.com/news/articles/2026-02-17/anthropic-says-new-ai-model-is-better-at-using-computers - Defense Department and Anthropic Square Off in Dispute Over A.I. Safety (New York Times): https://www.nytimes.com/2026/02/18/technology/defense-department-anthropic-ai-safety.html - Cyber Stocks Slide as Anthropic Unveils 'Claude Code Security' (Bloomberg): https://www.bloomberg.com/news/articles/2026-02-20/cyber-stocks-slide-as-anthropic-unveils-claude-code-security Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

New CLI auth commands streamline credential management, while Anthropic faces a Pentagon contract dispute and closes a massive funding round. In this episode: (00:00) Introduction (00:42) Claude Code Updates (02:17) Under the Hood (03:30) In the News Further reading: - Behind the model launch: What customers discovered testing Claude Opus 4.6 early (Claude Blog): https://claude.com/blog/behind-model-launch-what-customers-discovered-testing-claude-opus-4-6-early - Claude Enterprise, now available self-serve (Claude Blog): https://claude.com/blog/self-serve-enterprise - Anthropic Pushes Its Valuation to $380 Billion With New Funding Round (New York Times): https://www.nytimes.com/2026/02/12/technology/anthropic-valuation-380-billion-funding.html - Pentagon threatens to cut off Anthropic in AI safeguards dispute, Axios reports (Reuters): https://www.reuters.com/technology/pentagon-threatens-cut-off-anthropic-ai-safeguards-dispute-axios-reports-2026-02-15/ - Exclusive | Anthropic Takes Big Step in AI Race to Reshape College Coding Courses (Wall Street Journal): https://www.wsj.com/tech/ai/anthropic-takes-big-step-in-ai-race-to-reshape-college-coding-courses-04c48372 - Anthropic AI safety researcher quits with 'world in peril' warning (BBC News): https://www.bbc.com/news/articles/c62dlvdq3e3o Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.

Claude Opus 4.6 arrives with experimental agent teams and automatic memory, while Anthropic closes a massive funding round and partners with Goldman Sachs and Apple. In this episode: (00:00) Introduction (00:42) Claude Code Updates (03:05) Under the Hood (03:57) In the News Further reading: - Building a C compiler with a team of parallel Claudes (Anthropic Engineering): https://www.anthropic.com/engineering/building-c-compiler - Behind the model launch: What customers discovered testing Claude Opus 4.6 early (Claude Blog): https://claude.com/blog/behind-model-launch-what-customers-discovered-testing-claude-opus-4-6-early - The Week Anthropic Tanked the Market and Pulled Ahead of Its Rivals (Wall Street Journal): https://www.wsj.com/tech/ai/the-week-anthropic-tanked-the-market-and-pulled-ahead-of-its-rivals-ef59dff1 - Goldman Sachs teams up with Anthropic to automate banking tasks with AI agents (Reuters): https://www.reuters.com/business/finance/goldman-sachs-teams-up-with-anthropic-automate-banking-tasks-with-ai-agents-cnbc-2026-02-06/ - Apple adds agents from Anthropic and OpenAI to its coding tool (CNBC): https://www.cnbc.com/2026/02/03/apple-adds-agentic-coding-from-anthropic-and-openai-to-xcode.html - Anthropic's more than $20 billion funding to close as soon as next week (Reuters): https://www.reuters.com/technology/anthropics-more-than-20-billion-funding-close-soon-next-week-bloomberg-news-2026-02-07/ Claude Notes Brief is a weekly podcast covering Claude Code updates and Anthropic news. Subscribe at claudenotes.co.