Oh, no! Chuck’s program went rogue, escaped containment and hacked into municipal water systems! No worries, they’re blaming it on Iran.
But on a more serious note, it does seem that AI assistants like Claude Code or even the much dumber ones like Gemini are quite good at coding tasks. Or coding adjacent tasks like I have been configuring
a couple new Linux servers and my skills in that area are rusty plus what worked in CentOS6 doesn’t necessarily work in AlmaLinux10.
On other types of tasks though, it still bothers me how they will confidently tell pants on fire lies. If they don’t understand the prompt, or don’t know the answer, they will just make shit up. And since
they’re good at language, they are very convincing liars. Or is the new word fabulist, ever since George Santos? (and Harold Hill, in case you thought this was a new problem)
Wrote (better, described a desired outcome) my first AI program today for an ESP32. Holy cow was that fast and easy and seemingly perfect. Have not tested it yet but looks good.
So easy... wow!
