Nate McMaster

A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…

We've rolled out a new auto-memory feature. Claude now remembers what it learns across sessions — your project context, debugging patterns, preferred approaches — and recalls it later without you having to write anything down.

#ClaudeCode job opening - We're looking for someone who has *built developer tools that run on Windows* — think CLI apps, PowerShell integrations, terminal tools. Someone who is passionate about the Windows developer ecosystem would be ideal. job-boards.greenhouse.io/anthropic/jobs… #Anthropic

It just keeps getting better

Claude is built to be a genuinely helpful assistant for work and for deep thinking. Advertising would be incompatible with that vision. Read why Claude will remain ad-free: anthropic.com/news/claude-is…

After a 3 month lapse on @1Password, I'm back to using it. It was hard to get rid of the muscle memory of CMD+\ . Apple Passwords is just not as good. natemcmaster.com/blog/2026/01/3…

New post: "So, you want to work for Anthropic?" Sharing my experience with the application process and balancing trade-offs around income, popularity, hype, and uncertainty. natemcmaster.com/blog/2026/01/2…

We’re publishing a new constitution for Claude. The constitution is a detailed description of our vision for Claude’s behavior and values. It’s written primarily for Claude, and used directly in our training process. anthropic.com/news/claude-ne…

CommandLineUtils v5.0 released today. Thanks to all the contributors who added features and bug fixes! github.com/natemcmaster/C… Most noticeable change - faster startup if you've set PublishAot=true in your project (kudos to @robertmclaws)

@AnthropicAI is investing $1.5 million in the PSF, focused on security. These funds will make an enormous impact on the PSF and the security of millions of #Python and @pypi users. Please join us in thanking Anthropic for this landmark gift! Read more: pyfound.blogspot.com/2025/12/anthro…

@robertmclaws I'm thinking we'll push as a stable release at the end of the month, tracking in github.com/natemcmaster/C…. Download metrics suggest we get very low volumes of prerelease usage, so we'll fast-follow in Feb. with 5.1 if there are unintentional breaking issues.

@natemcmaster Thanks for your support Nate! Been going all-in on AOT for AI tools and I’m glad my favorite CLI library was open for contributions. 🤜🏻

Big thanks to @robertmclaws for building the AOT support into CommandLineUtils library! (github.com/natemcmaster/C…) This is now available in the latest 5.0 beta prerelease: nuget.org/packages/McMas…

Claude Code 2.1.0 is officially out! claude update to get it We shipped: - Shift+enter for newlines, w/ zero setup - Add hooks directly to agents & skills frontmatter - Skills: forked context, hot reload, custom agent support, invoke with / - Agents no longer stop when you deny a tool use - Configure the model to respond in your language (eg. Japanese, Spanish) - Wildcard support for tool permissions: eg. Bash(*-h*) - /teleport your session to claude.ai/code - Overall: 1096 commits github.com/anthropics/cla… If you haven't tried Claude Code yet: code.claude.com/docs/en/setup Lmk what you think!

@robertmclaws @nickproud It's looking good so far @robertmclaws. I found an hour over the holiday weekend to take a look. Hopefully should complete the review in a week or less and get a beta up on nuget to test

@nickproud Been doing a lot with Native AOT lately. It’s kind of a PITA but the perf is worth it. Will be great for console apps, especially once @natemcmaster’s new gig settles down and he can review my AOT PR for his console utilities. 🤜🏻

.NET devs: Native AOT is no longer “experimental”. Faster cold starts are becoming the norm in some scenarios. #dotnet #softwareengineering #performance

Normally I cheer for Liverpool, but a goal this good by Reed still made me cheer #PremierLeague

I’m seeing some hot takes that AI assisted coding means that you don’t have to be technical anymore. That’s only gonna last you until the first database migration, or the first security issue, or the first cloud migration, or the first scale out, or the first major regression, or the first refactor that ends in slop. I am finding that I’m learning more and I have to be as technical or more technical than ever before to get the kinds of high-quality output that I expect of any code, regardless of whether it comes from my fingertips or someone else’s - including an AI. Whether your source comes from open source libraries, your own hands, or an AI via your clever prompt, there is exactly one responsible person for the output. That is you. I never want to be accused of gatekeeping AI assisted programming, as non-technical people can get a lot of interesting work done. Until they hit a wall, and it’s gonna surprise them how quickly they either need to get technical, or get a technical person to help untangle the mess they’ve made. The art and science of programming is taking intent and turning it into shipping products. I will never blame an AI - nor should you - for bad output. Own the code that you ship.

I'm joining Anthropic as a Member of Technical Staff. After 6.5 years at AWS, people asked why I'd leave my role as a Principal Engineer. Wrote up my FAQ. In short: I believe in Anthropic's mission and want to contribute. natemcmaster.com/blog/2025/12/3…

tidyfirst.substack.com/p/programming-… A good post on #ai for software devs that I think resonates with me

This resonates with me as a principal engineer in internal tooling at AWS. lalitm.com/software-engin…