[airstrike]

That's precisely the problem.

People are building UI/UX for a paradigm that is so utterly new that they miss the mark entirely.

Everyone defaults to a big chat input because that's all they know. It's the expectation, so it's safer, faster, and cheaper to not deviate.

It's also wrong and bad for work.

[datakan]

> It's also wrong and bad for work.

Say's who? Why? I honestly don't get the problem. OpenAI just did what you said with the Mac app and were forced to roll it back because of the uproar. A chat box is simple, relatable, easy to use. K.I.S.S. is a thing

[airstrike]

> Says who.

Says everyone who's not using this stuff. It's an empirical argument. Is anyone actually using this for work? How long has it been since Cowork was released?

It's such an inadequate tool for work it reeks of SF hubris to think you can just slap a chat input box onto a PC and replace 90% of white collar jobs.

[cortesoft]

A CLI interface has been perfect for my coding work, why is it bad?

[airstrike]

it's pretty great for coding because the CLI provides the model with all the context it needs and with a way to verify the result of its actions via linting, compiler messages and program output

the rest of "work" doesn't have that luxury

[dymk]

Copying a block of multi-line text out of the agent doesn't work over ssh, for instance.

[o0-0o]

How would you fix it?

[airstrike]

Models need richer context to do well. They also generally need a verifier, but better context is already an improvement. So to fix it, you need to rethink UIs to be agent-first.

I'm not saying Kimi Work and its peers are entirely useless. I'm just saying they're a hack that puts a pretty low upper limit on agent capabilities and speed.