ever since the twitter algo dropped I keep getting comments on my pinned post.
so if you are an LLM / AI / BOT or otherwise, please say so I can block you.
@gcduncombe nice
this reminds me of the time I made a tool for stop motion / timelapse videos to remove frames with hands from video
it might improve the output as the hand could throw off the ai
testing various theme colors, claude was smart enough to see that modifying the html is wonky and instead rewrote the html in a modular way so iterating color themes is much easier!
it actually saved me tokens and time
๐๐ฆ๐ ๐ถ๐ ๐ต๐ฒ๐ฟ๐ฒ - ๐ถ๐'๐ ๐ท๐๐๐ ๐น๐ผ๐ ๐ผ๐ป ๐ฏ๐ฎ๐๐๐ฒ๐ฟ๐ถ๐ฒ๐.
---
the thing with AGI is the bar keeps getting raised
yesterday's AGI is today's mediocre LLM
most models today are capable answering virtually any question at PhD level
that within itself I would call AGI
when you factor in the fact it can do that for multidisciplinary fields simultaneously - that should be called ASI
let it ponder the questions of the universe and it will find answers (eg. multiple solutions to Erdos problems)
as long as you let the models run (ie. pay for tokens) they will continue to solve problems
ASI is here. the only reason we don't call it that yet is it's (thus far) low on batteries.
"roast my design then apply changes accordingly"
did not work the first time
but holy shit did it do wonders the second time!
try it!
one of the highest value prompts I've done
Holy crap, a Brazil municipal employee has discovered a 1000x faster way to finetune LLMs โ with a little weird trick! This is insane. Global South risingโฆ
Frontier labs hate him
@its_miro1 my brother you made only 13 posts all of them the same without even telling about your app and you expect to go viral?
you go viral by giving value, not by boasting and being boring