tempacct2cmmnt

I checked out at

“ This week is our argument for that claim, and we are making it in code rather than in prose.”

Doctor:

I don’t mind the questions. I mind the assertions of fact.

Agreed. Given how many significant errors LLMs make in my topic of expertise, despite my taking multiple error checking steps, the idea of catching 100% of hallucinations because you told the LLM to check itself is hilarious. It’s just a wild lack of insight: “I’m using the LLM to teach me something I don’t know about, I definitely have the knowledge base to spot any errors that might remain!”

I’m mostly amused they dropped this after the clusterfuck that was their new desktop app. My most recent ChatGPT experience is “wait, where did all my conversations go?!”. Concurrent enshitiffication is a bold move.

Many of them are prime real estate locations in large part -because- the old institutions are there.

I’ve had much better results with Kagi than with Google in the past few months. I’d trialed them a couple times in the past and been disappointed, but that’s no longer the case.

Benzodiazepines = memory loss Propofol = we turned your brain off

Nothing stops us from using both, where strategically appropriate.

You may have overlooked the small blue bar at the top labeling it an ad.

Wild that people will call a guy who bought SpaceX the founder of SpaceX.

Hey, just popping in as a psychiatrist:

Speak to your psychiatrist about atomoxetine, viloxazine, guanfacine, clonidine, bupropion, desipramine, or protriptyline. Probably in that order.