khimaros

this does not appear to be https://en.wikipedia.org/wiki/Subvocal_recognition

i am referring to Sam Altman's own words in his "Three Observations" post: "The intelligence of an AI model roughly equals the log of the resources used to train and run it."

https://blog.samaltman.com/three-observations

https://github.com/bigscience-workshop/petals was meant to be this i think

that was always the promise wasn't it? linear increase in intelligence in exchange for exponential increase in compute?

and can still be achieved locally with llama.cpp for example. one extra json parameter.

though not nearly as popular of an expression in that category as μαλάκας

this existed long before beads

that sounds great and looking toward to it. is there an issue i can subscribe to?

see also: https://github.com/dspinellis/git-issue

same question here. the other limitation i ran into immediately was only having two status types: open and closed

created something similar but specific to llama-server. it takes advantage of logprob output and completes decisions in a single forward pass https://github.com/khimaros/verdict

i built something with a similar philosophy https://github.com/khimaros/hrns

I killed my own ssh session twice with pkill -f, because the pattern matched the command line containing it.

i have owned nearly every Google phone since the G1. i will not be purchasing any future devices from them unless they change course.

to be honest, i hadn't affirmatively diagnosed, but i'm glad i mentioned it because another Glider user corroborated!

@danielhanchen may be able to answer this

these links never work for me. always "Error: Enter a valid URL" when opening in Firefox. maybe a URL escape issue with Glider?

lightning is sparse, glimmer is dense

seems to underperform on Terminal Bench compared with qwen3.6-27b: 51.7 vs 60.7

*someone in the energy sector

also, i don't necessarily mean to endorse this worldview in terms of its potential impact on policy, though there may be some truth to it, technically speaking.

sometime in the energy sector once told me "the solution to pollution is dilution"

pi also installs and runs just fine

this seems to be an advertisement for Modal. is it really your own infrastructure if the hardware is leased?

sounds like Japan

i have this pet theory that it was inspired by BitchX (they prominently mention being like IRC)

i prefer to call her Claudia

https://github.com/khimaros/flow if you're looking for a more streamlined and minimalist alternative to n8n. it also has CLI integration with piped input and output. user nodes can be written in Typescript, Python, and Rhai in addition to fully declarative nodes. UX it's more similar to ComfyUI

wouldn't incant/incus be a better drop in?

related and possibly more general purpose https://github.com/t8/hypura