transhumanist building cogniclankers | prev @ redacted
Joined September 2026
- Tweets4.2K
- Following201
- Followers191
- Likes4.2K
i stg most agents.mds and skill.mds are eng astrology, like have these ppl ever studied context and compaction dynamics
bro... we have reached the point where open models smoke the models i had access to when i was working on curing an incurable disease
im playing with mimo-v2.6-pro rn, and its so much better than anything i had back then, its better than the deep research i had back then bro
i gives me a lot of bullshit, but it also gives me nearly everything worth reading ~immediately, and if you already know the subject so well, it literally only costs you a fraction of a second to file a claim as bullshit and move on
like, i dont think ppl understand where were at bro, i rly dont, this is legit absurd
now, to be clear, this is very easy for me to say, im dramatically more skilled in the subject that i was back then, so my ability to formulate prompts is nothing like it was back then, that too may be playing into this, but there rly are some industry-wide improvements across all models simple intelligence doesnt account for, tool call efficiency and long running task perf being the most obvious examples
the more i get into context and compaction the more i realize just how unfathomably idiotic most skill stacks are, all prior skill stacks of mine absolutely, beyond a shadow of a doubt included
i dont know why but failing experiments feel rly different in ai than they did in neuropharm, i never rly felt disappointed in neuropharm, id just immediately move to the next thing, here there is a bit of "fuck, is this even possible?" which i never rly felt in neuropharm, even though what i was trying to do was ~insane, and took literal years
> i cant see diffs in tuis like i can in guis
>> yes you can, have your agents open the diff view in vs code headlessly
> i cant leave comments
>> yes you can, you can number responses and paragraphs, or you can have shit open in vs code, or you can do a billion other things
> i cant
> yes you can just ask fucking opus
my agents are barred from using cloud agents completely, only with the exception of grok bot
but bro like im literally just using the default terminal, not even itemp or ghosty, like you cant fuck this up
literally just curl homebrew, brew install --cask claude-code@latest, use claude code, and whenever sth bothers you or seems inconvenient just ask opus how to fix it, and it will
like, this is not rocket science, i pinky promise
i stand behind this so hard, use any opportunity you get to use code over agents
i think this goes beyond company functions actually
i’d think of agents as a crude tool, an expensive solution to many problems, not a particularly elegant one
agentic solutions are slower, more expensive, and less certain than code solutions
i personally favor code anywhere i can put it, and leave to inference only what only inference can do
thank fuck you reposted this, i missed it yesterday somehow
its okay, necessary even, not to try ever model that drops
yk, ive reached shiny object syndrome exhaustion, yeah, theres like a bunch of shit that comes out, great, other ppl can fuck around with 80%, ill use the other 20%, and if everyone keeps bugging me abt sth, ill try it, like we all know what works atp, you dont need the fifth open release of the week to teach you
this profile is rly fun cuz the things im truly exceptional (neuropharm) are so specific theyre nearly instantly identifiable by any competent agent so we all get 98% unhinged me, 2% okay this guy may actually know shit
bro my hands are fucked, my voice is fucked, everything is fucked, like i cant type anymore, my right middle finger especially for some reason is completely fucked