Are you referring to GitHub Copilot? I believe this thread is referring to Windows Copilot, such as the AI feature embedded into every Office progam, which is not the same experience.
Try sending this prompt to "GPT 5.6 Think Deeper" in the interface:
Provide me with optimised python code to perform a prime number search. Test the code and report on performance. Benchmark different search solutions. Provide the code in a downloadable zip archive.
A silly toy example, but it should help give a hint of what's possible.
Just for anecdata: I'm using simplelogin to alias my emails and I can see there is a 20ish minute window between when Simplelogin receives an email, to when it finally shows up in my Proton inbox. Normally it's an inconsequential delay.
Not sure if that indicates how much of a backlog of emails Proton has because of this outage, or if the DR infra is just that much slower?
Sure, this is (mostly) about direct contributions to Debian.
Proposal C does discourage use more broadly but acknowledges that many upstreams take a different view and that it would be impractical to ban them from using it.
I have very little in my agents.md file wrt style, except for:
> Caveats belong inline, no "one thing to note" or "it's worth mentioning" footer. If it is worth raising or calling out, do so where it is most relevant and not as a foot note.
Opus 5 has a god awful habit of always doing a Columbo on every single response, and it is such a jarring read that it amps my cognitive burden having to back-read everything.
The (many) interior designers we consulted before renovating our house used A/VR to show us what those changes could look like. The AR experience was the most surreal and useful, though.
Which have ignorance as their root cause. Ignorance of the type of people that become ultra wealthy, and ignorance of the odds of becoming one of them.
We should “listen” to these people with the same attitude as we do”listen” to gas station lottery addicts, instead we give them WAY too much credibility.