Re:Going full AI engineer, not touching code anymore
by tidewinner on Tuesday May 19, 2026 @11:02AM
(#48194290)
The people who I work with who have gone full LLM prompt engineer are the people who produced low quality, sloppy work. Generally they never liked to be challenged and never appeared to put much effort in.
The same people might have put some effort into responding to a code review before, but now they just prompt the LLM with 'is this a valid point?' and respond with whatever it hallucinates.
These are the people that are hard to work with.
First thought reading this was yes it's rage bait.
Re:Going full AI engineer, not touching code anymore
by yehosef on Tuesday May 19, 2026 @10:48AM
(#48194049)
can an architect review a system he didn't design or build?
Re:Going full AI engineer, not touching code anymore
by mariopt on Tuesday May 19, 2026 @11:05AM
(#48194320)
If you never coded that architecture yourself, you are not able to tell if it fits the problem, pros and cons, if the implementation is in accordance.
Imagine reviewing CQRS without having built one
Re:Going full AI engineer, not touching code anymore
by doug_durham on Tuesday May 19, 2026 @11:05AM
(#48194323)
You are choosing to be enraged. If a tool works it works.
This idea of reviewing an architecture that you never coded is just a fantasy.
At some point in time, me and a lot of people, thought that using Redux was a great idea until we had to manage verbosity and middlewares. Now we had to deal with the consequences of our decisions and we learned.
I also think this article is just a rage bait