3 × 1.01⁵² = 5.03 hours per week at the end of a year if you did 1% more than you did last week if you're already doing three hours a week.

Another pointless "up to x% better" specification.

I've started to go stand in my front yard and just watch the world go by for 15 minutes or so and if I do it around dinner time then I can get away without looking weird as it's perfectly normal to wait uber eats this way.

It's your yard though, you can stand in it whenever you want.

Which bit? The short sentences?

Not just the length but the structure, the way the headlines are phrased, the use of "honestly", the "not X but Y", many things cumulatively, not one particular thing in itself. If you work a lot with LLM writing, you notice. Same way you recognize the writing style of famous authors. It's never one particular thing but many.

Also love my muhle safety razor. Also prefer rim brakes over disc on my bicycles. Steel frame bikes. Drive a 2001 corolla. Use a denon 2308 avr amp from 2008. Run hdmi from mini pc into a smart TV that's never seen WiFi or the internet. Run optical from TV into the avr, 3.1 setup. No soundbar. No stream. Everything simple and reliable.

Stare at the wall and think about what I'm actually solving.

What's next, Dog Pause?

That's unfortunate to hear. This has allowed me to connect with talent that has otherwise not been given the opportunity to showcase their skills. At the scale I'm doing it it's pretty harmless but can see how it can be easily exploited.

I’m jaded, and I shouldn’t let it show :)

One only needs to encounter a handful of bad actors to paint everyone with that brush - perhaps unfairly. Best of luck to you.

Me too. It doesn't have ability to alert only on true positive. I has to also alert on true negative. So dumb

This doesn't seem to hard to solve except for the ever so recurring llm output validation problem. If the true positive is rare you don't know if the earthquake alert system works until there's an earthquake.

... just force the data into a structured format, then use "hard code" on the structure.

"Generate the following JSON formatted object array representing the interruptions in my daily traffic. If no results, emit []. Send this at 8am every morning. {some schema}. Then run jsonreporter.py"

Then just let jsonreporter.py discriminate however it likes. Keep the LLMs doing what they are good at, and keep hard code doing what it's good at.

Slightly related, I was using an LLM to help me understand whether I should add milk to my coffee before walking to my table or when I get to my table (objective to maximise coffee temperature at the point drinking). Turns out it's best to add the milk immediately when the coffee is made because the rate of cooling is higher at higher temperatures.