Caleb McKinney 🐁

@owengretzinger @boardyai GenZ yearns for the HelperBot

linkedin feed rn 📦⭐️

I read this in art school ages ago and this is more important than ever in making software.

@maxhodak_ They built power plants of mammoths…

the humans didn’t hate the mammoths; in fact they probably worshiped them. they just thought their atoms could be repurposed for more important uses

@DavidSHolz Midjourney Scanner results should be visualized like the Everything video

this might be my favorite video ive ever made. i was making web visualizers for every part of our stack and i added a zoom and said "whoa this looks like a Max Cooper music video" then i got license to a Max Cooper song, added some technical narrative subtitles and ahhh 🥺❤️❤️

Baby has gotten good at identifying “dada” but still struggling with surrealism, cubism, even baroque.

@krishnanrohit it’s only programming if it’s made in the champagne region of the human brain

From nature.com/articles/s4146…

Excited by gut-computer interfaces

@noahlt I recently had Claude use the contraction "I're". Probably a lot of the frontier weirdness comes from distillation / quantization

Fun when I get hallucinations from LLMs these days. Feels like hitting the edge of the map, exploring, relying on myself.

@om_patel5 This but code golf ⛳️

I taught Claude to talk like a caveman to use 75% less tokens. normal claude: ~180 tokens for a web search task caveman claude: ~45 tokens for the same task "I executed the web search tool" = 8 tokens caveman version: "Tool work" = 2 tokens every single grunt swap saves 6-10 tokens. across a FULL task that's 50-100 tokens saved why does it work? caveman claude doesn't explain itself. it does its task first. gives the result. then stops. no "I'd be happy to help you with that." no "Let me search the web for you" no more unnecessary filler words "result. done. me stop." 50-75% burn reduction with usage limits getting tighter every week this might be the most practical hack out there right now

@sawyerhood CTO simulator

why is every dev tool turning into fucking apple mail

@ericmitchellai thinking machines that build thinking machines that build thinking machines

machines that build machines that build machines

@onsoc63 @nabeelqu Hyperstitioned

@nabeelqu I am shocked as to how little have people updated their views on LessWrong. maybe they willed it into existence. that is the only good counter argument

Current events are just 2010s LessWrong essays irl now, it's all playing out before our eyes