two priors, the easy mean is the risky mean + k and k has some positive value constraint

Speaking of keeping the focus in the code, not the chat, I saw this clip of a new nvim pkg "99" that's more my style maybe. A prompt buffer appears only briefly, and you can still work while an LLM fulfills some request asynchronously.

youtu.be/ws9zR-UzwTE?...

And I guess it's easier with LLMs to create your own integrations.

For example this Claude \in Nvim pkg github.com/greggh/claud... lets you bind a fn to send a visual selection into the chat prompt. Stuff like that is good. I want to be in the code, not in the chat.

LLMs don't scare me, executives do

I need to be bombarded by unsolicited rage bait but in an ethical way

I suppose this is also less clunky then popping an element only to maybe re-append it

de-structuring the tuples here creates a more pleasant reading experience

i shall spare you from my blegh

join the vim gang and control everything

editing the clip: "hard rule: no statistics... it isn't worth it"

my worry is that this is good armor against slop only to the extent that people have collective energy to join hands and hate it together, which is a shaky foundation

the work is never done, matt