| Blog | https://ryanparsley.com |
| GitHub | https://github.com/RyanParsley |
| BookWyrm | https://bookwyrm.social/user/RyanParsley |
| Codeberg | https://codeberg.org/RyanParsley |
RE: https://neuromatch.social/@jonny/116667022863059853
Excellent thread on what "LLM-assisted" testing actually does, with context from rsync replacing its test suite with a poorly vibe-ported Python version (as regressions roll in)
More generally, the primary product of LLMs is deception: the unfounded belief by the insufficiently-critical observer that the task has been performed. From vibe-coders to user communities, managers, and investors, there are many targets of the deception. Many are playing along for their own self-interested reasons (e.g, executives need investor confidence more than they need a product). And many feel hit when peers and communities see through it.
"I’m here to tell you the mission of your generation is to destroy AI"
What if the real key to getting better results with AI coding agents is boring stuff from the 1990s?
Would it help if we called it "feedbackmaxxing"?
I very much enjoy The Pragmatic Programmer. I think this book aged very well and even the apocryphal allegories are useful.
A clanker called me "pragmatic" and it made me angry. I was offended by the accusation.
Jed Brown
Malte Engeler
abadidea
Jason Gorman
Max Leibman
paul