Sorry, the text is too vague - what are they building exactly, another tmux?

P.S. That custom disappearing scrollbar doesn't look super logical; it doesn't even look logical, tbh.

Yes. I find it quite funny that 4 people with the flashiest of titles (head of experience?) came up with this amazing plan:

1. it will be incredible

2. it will be composable

3. it will be safe to use in production

I would totally invest millions into these guys, they have a bright future ahead.

My first thought was that they have several people who seem like they'll expect very serious compensation but no actual product, then I noticed they already seem to have a whole bunch of VC backers. I'm not gonna lie, I'm a little jealous of people who can make a flashy vaporware pitch deck and ride the VC gravy train.

I feel like it must be worthwhile for Hashimoto to move on from Ghostty to this.

If it is ‘just’ a better tmux-like experience, then that could be very useful if these agentic workflows actually arrive.

I still don't understand why tmux authors wasted their time on tmux, tho, when we already had perfectly servicable GNU screen.

Why reinvent the wheel?

/s

"China is bad"? I don't know, man. I'm not buying it.

Do you understand every line of code written by everyone else on your team? I doubt it. But if you ever need to work with their code, that's when you might need to understand it. So, treat an AI agent like another teammate.

I think a wiser approach for crossing a border might be to have another phone with regular Android installed on it, so it doesn't look suspicious, and then connect remotely to your main phone. Before crossing the border, you would just need to remove the remote-connection app, and after crossing, install it again.

  > Why spend years mastering language intricacies when an AI can generate code in any language on demand?

You can learn relatively well any programming language in a week. You don't need to master "language intricacies".

Claude Code gives you more control - you can disable auto-memory temporarily (nothing will be deleted), then enable it back; or you can setup a directory where auto-memory is disabled and do your throwaway there.

And I am going to do nothing. Works fine.

Good to know, but looks less readable than `if` example.

My gut feeling is that OpenAI tells the truth in this particular case. Yes, of course, they use this story for marketing but it doesn't mean that they are lying.