Hacker Newsnew | past | comments | ask | show | jobs | submit | snissn's commentslogin

they should run their test against a control baseline such as an open source hosted model to see the overall drift in their test

reply


https://gist.github.com/snissn/4f06cae8fb4f4ac43ffdb104db192...


I’ve found throw the problem at 3 o3 pros and have another one evaluate and synthesize works really well


So like, a whole forest of trees per query is what we're saying here?


Ideally just a few split atoms


Now You’re Playing With Agent Power!


I'm impressed with how easy it is to recreate this effect using AI tools. I made this on my iPhone in the photos app by circling Garfield a few times: https://i.imgur.com/YVOZlj8.jpeg based on https://www.gocomics.com/garfield/2025/04/10


The physical act of removing the Garfield figure from the frames is the least interesting part.

(It probably also isn't particularly difficult in many cases, considering the monochrome backgrounds.)


to also share a reference - here's an on disk hashmap that uses mmap that I made in golang: https://github.com/snissn/gomap


Human + ai writing tests >> human writing tests


37 million Kelvin


this is worth a read too https://en.wikipedia.org/wiki/The_Noid


Here's a demo of my project shape faces https://shapefaces.com/


new line seperated json "JSONL"


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: