Ted Carstensen

@mitchellh@hachyderm.io congrats ❤️❤️

auto mode on max when

There’s a certain poetry in Adobe messing with my hosts file today as a fully paid user when years ago I would edit my own hosts file to black hole their license checks

“compression and decompression, otherwise known as codec.”

I have worked in video production for essentially 30 years and I did not know this is where codec comes from 🤯

https://daringfireball.net/linked/2026/04/02/buck-quicktime-history

@finnvoorhees this is rad - a killer feature for me would be Navi helping me across tab groups - I’m interested in automatically/regularly reviewing all open tabs and cataloging them into project-specific obsidian docs. Any agents who end up working on the project will have all the links available, and I don’t always have 150+ tabs open across multiple groups. Tab groups seem out of bounds for so many tools, are there limits on interacting with them?

if I upgrade to max 20x will they let me have multiple chat/cowork/code windows open at once like I can with code in ghostty?

IYKYK

One sneaky but powerful aspect of skill.md’s I’m reflecting on is that they’re as effective as the model leveraging them. So as long as the skill is well crafted, you should expect better results ‘for free’ every time a new model drops

RE: @arstechnica@mastodon.social

This must have been part of the Gemini deal?

Working on an exciting project that touches hundreds of transcripts this week (alongside at least three other 'normal' context size projects in parallel) has put me in claude jail repeatedly. Agent teams are amazing, and they have made it clearer to me than ever that more tokens=more speed. I have *way* more ideas than I have tokens, so if we desired we could simply pay to move faster *without losing quality of output*, it's wild.