See lots of comparisons to Ansible but Chef/puppet (both of which have agent-less modes) in Python instead of Ruby is what immediately came to mind. I guess Salt as well technically.
Agrees? I appreciate your efforts at painting me as a freak, but could you please quote the exact part of my reply that in your optinion supports your claim about my agreement with the Protocols?
I think it can sort of make sense for some people who sort of listen to music as a background noise. But for me, when I am listening to a new song, I get curious about who the artist(s) is/are. Do they sound better in a live performance? What other music or artists inspired them? What other artists sound like them?
I don’t think it would be easy for a “AI” artist to not be suspicious to me unless they were like some kind of character that is made up by a record label or another artist.
I'm the opposite (I know, it's probably bad) but I often do everything I can to not know who's behind because I often try to dream and make my own mind about a specific song/artist, and of course my wife then suddenly show me who the person is and then the whole perception of the artist changes and sometimes ruin it for me.
I listen to music from night to morning (practically non-stop actually) and probably 100+ different artists within a day, I'm not genuinely interested in them, I'm just interested in their work.
> I think it can sort of make sense for some people who sort of listen to music as a background noise
This is a whole genre of music in of itself that real people created which AIs were trained on stolen copies of to produce slop that doesn’t have to compensate the origins.
So it only makes sense in that case if you think slop derived from real art is awesome and that actual human beings can get fucked.
> For me personally, I don't really know. You can't just do the same thing because the economy is constantly evolving, but I can't see where it's going.
You’re not alone, I’ve absolutely seen the same behavior occasionally with Opus in OpenCode where it takes actions it shouldn’t be able to in plan mode.
Considering it happens across both opencode and other apps like Claude and Codex as well as across models it seems like something inherent to the models themselves and not necessarily a bug in the apps wrapping them. But maybe there’s more opencode et. al could be doing to prevent it.
The harnesses are the part of the stack responsible for tools, so it would be a bug there, not the model. The model itself isn’t doing anything but generating tokens. The harness gives it a blob of text telling it which tools exist, and the model may choose to tell the harness to call one.
“Plan” vs “execute” modes seem more like suggestions the models _mostly_ follow. I have absolutely had models (Codex and Sonnet/Opus) perform actions in plan mode they should never have been able to take like editing files or starting to work on a plan that was just created.
reply