Brian Woodward -makes open source used by millions

Software developer. Building software that enables building software and systems. Follow me for updates, here and at

[Brian Woodward -makes open source used by millions @doowb]

@Jonathan_Blow @notch @housecor With AI, each test contains a mock and spy of the function (and any internal calls). This ensures the function returns what the AI will assert is expected.

[Brian Woodward -makes open source used by millions @doowb]

@HistoryBoomer Reminds me of the "The Mandela Effect" movie

[Brian Woodward -makes open source used by millions @doowb]

@elonmusk cool, so the feature is padding the fare by driving down dead end streets?

[Brian Woodward -makes open source used by millions @doowb]

I got a nice email from GitHub support once asking me to throttle my requests. I think I was testing a script that pulled all the issues across all the orgs/repos I was connected to and forgot a timeout or to limit or something.
This was before the graphql api and M$.
It really was a nice and friendly email. Now, I don't think a human would even be involved.

[Brian Woodward -makes open source used by millions @doowb]

Whenever I see an AI respond like above, I think of this:
https://t.co/0NoaK8k3KT

[Jon Schlinkert - creating an education platform @jonschlinkert]

The agentic AI future we deserve.

[Brian Woodward -makes open source used by millions @doowb]

After `gpt-5.4` updated a helper function implementation to be entirely incorrect, I asked why and was told that it "inferred" the correct signature from the documentation. I asked it which documentation and pointed out in the documentation, I gave it, the correct signature.

It's response was:

```
I misread that while refactoring and changed the helper instead of changing my new code, so I’m reverting the helper API and fixing the code to call it correctly.
```

How does it "misread" something!?!?
Is this what they mean when they say AI will replace developers?

[Brian Woodward -makes open source used by millions @doowb]

A few weeks ago, I noticed an "extension" running in the desktop app.

I tried to chat with their agent on the site and it kept referring me to the docs about the excel extension for higher tier plans. I started chatting with claude directly to see if I could find out more because I couldn't disable or uninstall the extension.

All I was getting was an error that looked like it was trying to contact the extension's MCP server. I looked through the configs and the logs where I had other MCP servers configured, but there was nothing there.

I finally determined that Anthropic installed something during an update that was probably supposed to be for their own development.

It makes me worry about what else they install and I "opt-in" to without me knowing. What other information about my system are they sending? Are they sending that information outside of regular requests? Or just injecting it, like you mention?

[Jon Schlinkert - creating an education platform @jonschlinkert]

The agentic AI future we deserve.

[Brian Woodward -makes open source used by millions @doowb]

When using a LLM, how often do you start a question with, "Why did you"?

[Brian Woodward -makes open source used by millions @doowb]

@andrewchen This is one that @jonschlinkert predicted and has guided us to create some of our most used public projects:

- Enquirer: https://t.co/CT32ISBWxQ
- Micromatch: https://t.co/iiWHkwlPsd

[Brian Woodward -makes open source used by millions @doowb]

Read @jonschlinkert's full post and see an example:

https://t.co/smI9aZe4Sh

[Brian Woodward -makes open source used by millions @doowb]

"once you understand what LLMs are *actually* capable of, and what they are not, then you start to realize that they truly are just doing next token completion, and they have no real ability to reason." - Jon Schlinkert

[Brian Woodward -makes open source used by millions @doowb]

hey @AnthropicAI, what's the office-addin connector in Claude Desktop?
Why was it installed?
Why's it tagged as "LOCAL DEV"?
Why can't I uninstall it?
What else are you installing on my computer?

[Brian Woodward -makes open source used by millions @doowb]

Source: https://t.co/8g5AkZjc9P

[Brian Woodward -makes open source used by millions @doowb]

"While you might be 10x with LLMs, you're still competing with developers who are 10x without LLMs."
- @jonschlinkert

[Brian Woodward -makes open source used by millions @doowb]

hey @github why did copilot suggest a valid api key from a .env file in a different project?

[Jon Schlinkert - creating an education platform @jonschlinkert]

Typescript has caused more errors in AI generated code than anything else.

[Brian Woodward -makes open source used by millions @doowb]

I just asked chatgpt to explain what a stop token is.
It responded with, "Sure! "

[Brian Woodward -makes open source used by millions @doowb]

hey @SlackHQ is there a notification sound that won't give me a heart attack?

[Jon Schlinkert - creating an education platform @jonschlinkert]

Just released commit-whisperer, "An AI genius for generating meaningful git commit messages from repository state and user instructions."

https://t.co/P31cfEjFxA