this post was submitted on 21 Sep 2026
923 points (98.7% liked)
Funny
16272 readers
2150 users here now
General rules:
- Be kind.
- All posts must make an attempt to be funny.
- Obey the general sh.itjust.works instance rules.
- No politics or political figures. There are plenty of other politics communities to choose from.
- Don't post anything grotesque or potentially illegal. Examples include pornography, gore, animal cruelty, inappropriate jokes involving kids, etc.
Exceptions may be made at the discretion of the mods.
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I know a good deal about machine learning. Machine learning’s principle metrics define how inaccurate it is.
The sheer volume of air plane traffic means you will have constant mistakes in those predictions. Leading to short staffing and actual consequences.
Staffing is not what they've said they're using it for. Coordinating scheduling of flights to reduce waiting and conflicts is what I recall seeing.
They are extremely short staffed. Training takes 3 to 5 years. Very few eligible candidates and the Federal work force issues. This isn’t problem they can solve, because the problem is them, not the system.
I think we can all agree there are multiple aspects of a system as complex as aviation coordination in a large metro area that should be evaluated and improved upon when possible. I don't understand how what you're saying relates to what you're replying to
I guess they will have to train less people possibly. But idk their full reasoning in replying with that.
Which has nothing to do with this.
AI being used by incompetent people trying micro mange their failure will not end well given the circumstance.