HN user
Perfect case study for programmers desing long term critical systems. With all our fancy "frameworks", there is Voyager 1, who is 15.6 billion miles away running on simple logic with limited change options.
To Ai paraphrase Obi-Wan: I felt a great disturbance in the Force — as if millions of developer voices from the future cried out in confusion and despair, and were suddenly silenced. I fear something terrible has happened to the future of our craft.
In short before we Ctrl+Copy our way to StackOverflow or Forums or IRC and we got collection of responses between good and ugly. But made us think and read or talk to others.
Now we Ctrl+Copy into LLM into a room of hell.
If LLM function is useful but don't get addicted to like honey.
Probably best text I've seen in AI train ride recently:
""""" As companies rush to deploy AI assistants, classifiers, and a myriad of other LLM-powered tools, a critical question remains: are we building securely ? As we highlighted last year, the rapid adoption sometimes feels like we forgot the fundamental security principles, opening the door to novel and familiar vulnerabilities alike. """"
There this case and there many other cases. I worry for copy & paste dev.
Data sniffers always looking for some dirty washing.
Ok with some stats send in quality. But these days the more complex they get, they sound like printer Error blah blah. :)