alsweigart.bsky.social

Why should I read your AI-generated writing? You probably didn't even read it before you sent it to me.

Ah shit, I accidentally wrote a program that gave me AI psychosis: import time while True: print('Ha ha, that was funny and clever, Mr. Sweigart.') time.sleep(0.5)

Let's start saying this now and keep saying it: NO BAILOUTS FOR AI COMPANIES

Sweigart's Law of Vibe Coding: The portion of software engineers reading the code that AI generates and the portion of people who read Terms of Service agreements is the same.

I've been doing a lot of vibe coding experiments recently. The models are better, but I've only released like five apps and dozens are in the QA backlog. AI isn't a "free app" generator so much as a "free puppy" generator.

So... I gotta ask... 1) is "recursive self-improvement" as stupid of an idea as "AGI" and 2) have people heard of RSI and taking it seriously? Like, this is magic beans level of dumb, even for AI.

"My training data has a cutoff of September 2021. Therefore, I have no knowledge of events that occurred after that date." Lucky bastard LLM.

Passing my website login logs to Claude and asking it to look for "suspicious activity" brings up some light flags, but the amount of contextual information it can give me is one of those "huh, LLMs are kind of spooky capable at some things" moments.

Is orchestration of multiple agents in parallel a dumb idea? The way I use AI to code, I have the AI generate code, then I review it (or at least QA it), in a loop. The idea of letting agents step all over each other and vibe code large quantities unsupervised sounds insane.

LinkedIn has a "Looks like AI" button for posts: "They're not trying to remove slop, they're trying to make it better and collect data about who complains about slop, which posts are obviously slop, and which posts are believable."