For a deep dive

When ya upload a file to a Claude project, it just keeps it handy, so it can reference it whenever. I like to walk through a kind of study session chat once I upload something, with Claude making note rundowns in its code window. If it’s a book or paper I’m going to need to go back to a lot, I have Claude write custom instructions for itself using those notes. That way it only has to refer to the source text for specific stuff. It works surprisingly well most of the time.

Better yet, have your LLM of choice read the book first.

Switched to Perplexity a year ago, but I occasionally still go to Google just from muscle memory. Google’s aggressively unhelpful now - it’s kinda insane.

Removed by mod

Pres·i·dent /ˈprezəˌdent/

Rabbit season

Our Fall is quite autumnal.

For a second, I thought he was an elf or a Vulcan.

Train LLMs on large bulks of data that meet criteria for deletion, thereby shrinking like 100 petabytes to a terabyte, albeit imperfectly. That way, you have a collection of AI bots that you can chat with about all the deleted data. And I suppose the threshold for deletion is, “How disastrous could a hallucination about this be?”

This sounds like a semantic argument, so… definitions.

Authoritarian - 1) of, relating to, or favoring blind submission to authority

Slavery is blind submission. Forbidding authoritarianism isn’t authoritarian. Kinda like how destruction of the self (suicide) cannot be selfish, despite what some will argue.

Alright, Courtney, no need to shit on his grave.