I trained a 360M model to pretend to be a terminal

Re:I trained a 360M model to pretend to be a terminal by IanCal on Thursday October 22, 2026 @09:41AM (#50195203)

> How am I suppose to "run the JS code", manually writing it in my local JS console? Or is this just "Click the green button in the UI" but expressed in the way only a LLM would write it?

Probably by clicking the button that says run. It is not a weird way to say what they did.

[ Parent | on HN ]

Re:I trained a 360M model to pretend to be a terminal by embedding-shape on Thursday October 22, 2026 @10:06AM (#50195514)

> Probably by clicking the button that says run

I don't see such a button at all, all I see is text/image pills, samples and a "Commit" button, which the text correctly mentioned, but the other things the text mentions, don't seem to actually exist?

It is weird, a human wouldn't write such text on that page, or if they did, make the text reference actual UI elements, not what they talked about while building it.

[ Parent | on HN ]

Re:I trained a 360M model to pretend to be a terminal by nico on Thursday October 22, 2026 @10:59AM (#50196340)

There's two sections, an Image one and a Text one. The image one doesn't have a Run button, maybe that's where you are getting confused? The text tab does have it, so you can Run the code shown in the box. The button is at the top right of the element with the code

[ Parent | on HN ]