Made a simple agent harness (Similar to Claude code) in golang with some help from Codecrafters' Build-your-own-x
Was a fun and quick project, and got to learn about many interesting things, from how to make clis in golang, to implementing agent loops with persistent memory
Do check it out, link in the comments
Vector retweeted
my girlfriend and i love playing wordle, so naturally, i ended up building my own version.
i don't particularly like the nyt site, and everyone on the internet gets the same word every day. most alternatives are full of ads and aren't quite what i wanted.
it's clean, and you can play remotely with friends by taking turns guessing on the same board (even my mum plays it now).
my favourite part, though, is the word bank. it accepts some very questionable guesses, and if you're stuck, you get hints after three guesses that tell you just enough without giving the word away.
every word you solve comes with its meaning and etymology, and you can ask for harder words too, so it's a neat lil way to expand your vocab.
probably my favourite thing i've built so far, simply because i actually prefer using it over what's already out there.
give it a go (looks especially nice on mobile btw)
I'm cooked for today's exam, even though it's a subject I find genuinely interesting (AI)
But we ball
2
97
Type of shi that actually motivates you rather than the 100th "dar na tu bandeya" edit
always astonished how few people are aware that you can turn your life into an IRL 5000 chapter chinese-MTL'd cultivation epic web novel by waking up every day and doing like 2 hours of anki cards + hitting the gym for 1 hour
2
115
Vector retweeted
i've been desensitized to exams i don't even feel the stress last minute for the post procrastination lock in to kick in, well whatever nvm.
Vector retweeted
i've been reading quite a lot of research papers over the past couple of months (even got to help out on one), and i liked the idea of picking one problem and going deeper than necessary instead of building something i didn't need. so i tried that with prefix caching in llms. i built a profiler to see what happens between a coding agent and the inference engine, byte by byte, got some numbers, then spent way more time figuring out what they meant.
this is me summing all that up in a neat lil writeup (kinda long tbh).











