Donโt be beholden to one LLM basket.
Get yourself an Openrouter account, get yourself an open source harness like pi and get yourself educated.
I will die on this hill.
I agree with this. I already use different models for different tasks in part for this reason.
Never bothered with an OpenRouter account though, I just have accounts set with each provider.
And Pi is excellent. I actually find it much better than Claude Code.
did they silently decrease the subscription limits on codex? (in addition to reintroducing the 5h limit?) subscription models suck so bad when they can just change the terms and make the product shittier.
ive been dual wielding 2 accounts with some fallback shenanigans. on average its enough for me, but on heavy weeks its annoying. + it feels intransparent
Any runners on here? I mostly consider myself a trail runner, but of course train on roads, too. Good for 1โ2 races/year, more into running as a practice, a way to manage stress and stay fit.
I naively went into a work problem thinking that RAG was solved by the service offered at work, and wow was I wrong. Been a fun week so far experimenting with many different methods before doing the academic research, and it's been nice to be validated by outside research.
You've hit the nail on the head. But here's the mindblowing partโwriting isn't just about text on a page.
It's not about listing a bunch of facts to memorize.
Writing is about human connection.
And here's where it gets even more fascinating...
[parody, not AI]
Some writing yes, If you want to write a post saying why your company has a position yes; if you are documenting an API, does the average swagger page have a human connection factor?
If you are in X/FB, is any of your followers a "human connection"?
Then, in some spaces, say big corp communications, the terse, direct communication is desired, for example the quarter earning communication?
What about software?, what part of your browser gives you the "human connection"?
If writing (incl X/FB posts) is meant to convey "some human being did/saw/thought this and found it worth writing about", then AI undermines human connection and will annoy people. API docs, earnings reports, &c never conveyed that to begin with, so nobody will care about AI use.
I think slop is not taking the time to refine and polish and simply publishing something as it was handed to you by the #AInotesfollow. You use AI but the decisions should be yours. Otherwise it's #slopnotesfollow.
Determine what matters most and make a list of the no more than 7 things.
Do one thing well at a time, top down. Reprioritise as you learn more.
Notes:
If you half-arse a task and decide that'll do, it's evidence it wasn't the right priority. Learn.
Any sort of productivity, multi-tasking, app, solution type thing is a scam or a money grab and isn't needed.
People tend to remember 7 things well, but struggle with longer lists and particularly fail to remember things in the middle.
Deterministic code generation is fine by me. Quite happy to use templating systems for example.
Problems occur when randomness is introduced. If you can avoid that it should be less "icky".
Collected my helper functions to lozenge.el package, e.g. (โduckduckgo
"textlog") opens ddg. Lozenge is โ character. Others are
(โfind-file), (โgrep), (โgithub-search), (โshow-commit) etc.
I suggest looking around your area first, perhaps there are conservation groups already. Then, select among them which one focuses on native species that are most impactful to your place. ๐
i'm trying to express through a math equation the relationship between power, number of people, corruption and time. corruption = (time in a position of power * power)/number of people who have power
what do you think?