Re:I'm betting against AI agents in 2025, despite building them
by macleginn on Sunday July 20, 2025 @08:06AM
(#44624397)
This is a good point, but it seems, empirically, that most parts of a standard passenger airplane have reliability approximating 100% in a predefined time window with proper inspection and maintenance, otherwise passenger transit would be impossible. When the system does start to degrade, e.g. because replacement parts and maintenance becomes unavailable or too costly (cf. the use of imported planes by Russian airlines after the sanctions hit), incidents quickly start piling up.
[ Parent
| on HN ]
Re:I'm betting against AI agents in 2025, despite building them
by constantcrying on Sunday July 20, 2025 @08:15AM
(#44624460)
It's about what you do with errors. If you let them compound they lead to destruction, if instead you inspect, maintain, reinspect, replace, etc. you can manage them.
My point was that something extremely complex, like a plane, works, because the system tries hard to prevent compounding errors.
Re:I'm betting against AI agents in 2025, despite building them
by sarchertech on Sunday July 20, 2025 @09:57AM
(#44625246)
That works because each plane is (nearly) exactly the same as the one before it and we have exact specifications for the plane.
You can do maintenance, inspections, and replacement because of those specifications.
In software the equivalent of blueprints is code. The room for variation outside software “specifications” is infinite.
Human reliability when comes to assembling planes is also much higher than 99%, and LLM reliability creating code is much, much lower than 99%.
Re:I'm betting against AI agents in 2025, despite building them
by stavros on Sunday July 20, 2025 @02:04PM
(#44627669)
If you think human reliability when writing code is more than 99%, have I got news for you!
Re:I'm betting against AI agents in 2025, despite building them
by sarchertech on Sunday July 20, 2025 @09:47PM
(#44631069)
If you’re going by bugs per lines of code, I’m far higher than 99% reliable.
Re:I'm betting against AI agents in 2025, despite building them
by stavros on Monday July 21, 2025 @03:16AM
(#44632551)
When measuring the reliability of my vacuum, I don't go by component, so I don't go by line when I measure the reliability of my code.
Re:I'm betting against AI agents in 2025, despite building them
by sarchertech on Tuesday July 22, 2025 @12:43PM
(#44649681)
Ok if we measure uptime of the software I’ve written it’s far higher than 99%.
Re:I'm betting against AI agents in 2025, despite building them
by stavros on Tuesday July 22, 2025 @01:43PM
(#44650609)
Again, we're not measuring uptime. We're measuring how many of them had at least one bug.
Re:I'm betting against AI agents in 2025, despite building them
by sarchertech on Tuesday July 22, 2025 @02:59PM
(#44651547)
So if your vacuum had one component that was out of spec, but didn’t put it out of commission for any length of time, it’s 0% reliable?