mitchellh · TEXXR

Daydreaming about an entry MacBook Neo as a thin client for local LLMs and dev work on a maxed future Mac Studio. Apple is creating the best value hardware for local AI and it's amazing to think of consequences of that.

2026-03-05 View on X

Tom's Hardware

Apple unveils the $599+ MacBook Neo, with a 13-inch Liquid Retina display, an A18 Pro chip, side-firing speakers, a 1080p webcam, two USB-C ports, and Touch ID

Apple debuts a new entry-level MacBook at just the right time — Apple finally took the wraps off its long-rumored budget laptop.

View original

Daydreaming about an entry MacBook Neo as a thin client for local LLMs and dev work on a maxed future Mac Studio. Apple is creating the best value hardware for local AI and it's amazing to think of consequences of that.

2026-03-04 View on X

Tom's Hardware

Apple unveils the $599+ MacBook Neo, with a 13-inch Liquid Retina display, an A18 Pro chip, side-firing speakers, a 1080p webcam, two USB-C ports, and Touch ID

Apple debuts a new entry-level MacBook at just the right time — Apple finally took the wraps off its long-rumored budget laptop.

View original

We need corporate PR speak like this to stop. Execs need to talk to people like people. The dev community is filling in the blanks anyways, whether they're right or wrong. Just own your direction and move forward, don't hide behind corporate cowardice. https://www.heroku.com/...

2026-02-07 View on X

Heroku

Heroku says it is transitioning to a “sustaining engineering model”, as it focuses on “helping organizations build and deploy enterprise-grade AI”

Today, Heroku is transitioning to a sustaining engineering model focused on stability, security, reliability, and support.

View original

Heroku was revolutionary and I'll always remember them that way. They made a huge industry impact. So many incredible people worked there. The final PR could've been heartfelt, celebrating memories and strongly moving to another direction, but it was a soulless void. Shameful.

2026-02-07 View on X

Heroku

Heroku says it is transitioning to a “sustaining engineering model”, as it focuses on “helping organizations build and deploy enterprise-grade AI”

Today, Heroku is transitioning to a sustaining engineering model focused on stability, security, reliability, and support.

View original

The biggest issue with the Codex app is how easy it is to create a PR. The automatic “open a PR” feature of agentic programming in general (not just Codex) is creating an insane amount of burden on open source (see 3 slopfests closed today in Ghostty's repo). Please, stop this.

2026-02-03 View on X

ZDNET

OpenAI launches Codex for macOS, designed to be a command center for managing coding agents, and says GPT-5.2-Codex usage has nearly doubled since mid-December

ZDNET's key takeaways — OpenAI launches a Mac-only Codex app as an agent command center.

View original

The biggest issue with the Codex app is how easy it is to create a PR. The automatic “open a PR” feature of agentic programming in general (not just Codex) is creating an insane amount of burden on open source (see 3 slopfests closed today in Ghostty's repo). Please, stop this.

2026-02-02 View on X

ZDNET

OpenAI launches a Codex app for macOS, designed to serve as a command center for managing AI agents, and says Codex usage has nearly doubled since mid-December

ZDNET's key takeaways — OpenAI launches a Mac-only Codex app as an agent command center.

View original

At this point most of the programmers I respect the most are AI positive and finding a lot of value in it. And of course understanding the limits, as with any good tool. @tqbf, Kenton Varda, @antirez, and many more. This post is mostly perfect: https://fly.io/...

2025-06-03 View on X

Fly

A software developer explains how AI agents help automate tedious coding tasks, and addresses concerns like hallucinations, job losses, mediocre code, and more

Tech execs are mandating LLM adoption. That's bad strategy. But I get where they're coming from.

View original

Don't use Carta. Just don't. I don't recall the details of my experience many years ago and no longer have access to my corp email to dig it up anyways, so I'm just going to say trust me, you do not want to be using Carta. (Reminded due to the recent Carta drama)

2024-01-08 View on X

TechCrunch

Linear's CEO, who uses Carta to manage Linear's cap table, says Carta tried to sell Linear shares without his consent; Carta's CEO blames a rogue employee

“This might be the end of Carta as the trusted platform for startups” — Carta, an ambitious 12-year-old Silicon Valley outfit …

View original

For those who aren't aware: you write an OpenAPI manifest for your API, use human language descriptions for everything, and that's it. You let the model figure out how to auth, chain calls, process data in between, format it for viewing, etc. There's absolutely zero glue code.

2023-03-24 View on X

OpenAI

OpenAI rolls out ChatGPT plugins, including two of its own, a web browser and a code interpreter, and open sources the code for a knowledgebase retrieval plugin

We've implemented initial support for plugins in ChatGPT. Plugins are tools designed specifically for language models with safety …

View original

I've developed a lot of plugin systems, and the OpenAI ChatGPT plugin interface might be the damn craziest and most impressive approach I've ever seen in computing in my entire life.

2023-03-24 View on X

OpenAI

OpenAI rolls out ChatGPT plugins, including two of its own, a web browser and a code interpreter, and open sources the code for a knowledgebase retrieval plugin

We've implemented initial support for plugins in ChatGPT. Plugins are tools designed specifically for language models with safety …

View original