zodwick
Re:Show HN: Where Were We
on Sunday November 08, 2026 @06:02AM (#50412197)
super cool ! wished there were more haha
Re:The End of AI Frontiers
on Saturday November 07, 2026 @02:18PM (#50407174)
Not what i expected, but good read nonetheless
Re:Awesome repositories are no longer awesome
on Thursday November 05, 2026 @07:35AM (#50378359)
I'd like to add a third reason: SEO hacking
Re:Spreading Liquid with Three.js
on Thursday November 05, 2026 @06:26AM (#50377881)
Very cool work ! I was unreasonably disappointed by the element at the top ( header ) not being interactive thgh :_
Re:Jailbreaking my car's navigation system just so I can change the time
on Wednesday November 04, 2026 @11:07AM (#50367595)
I think there are two aspects:
1. like no I don't want my microwave sending random blips of location data to a server and no I don't want hyper-personalised ads on my coffe machine
2. I want my machine to do what I want and not be limited by random limitations set in the software, either intentionally or via incompetancy.
Re:Coffee's new status symbol is a machine without plastic
on Wednesday November 04, 2026 @11:04AM (#50367549)
good thread to lookup : https://x.com/levelsio/status/2088235859887726696
Re:Tell HN: Gemini trains on chat history, even for subscribers (perso...
on Wednesday November 04, 2026 @11:00AM (#50367489)
why am i not suprised
Re:Jailbreaking my car's navigation system just so I can change the time
on Tuesday November 03, 2026 @12:07PM (#50354695)
The revolution against shitty locked down software has begun and I LOVE IT
Re:Show HN: I made a card game where you use cards to make a target nu...
on Thursday October 29, 2026 @09:02AM (#50288295)
CafeBench: Sol 6.1 is great value, but not quite Opus level
Re:Read the History, Not Just the Code
on Wednesday September 30, 2026 @03:54PM (#49913461)
i remember (pre AI) looking at PR history before reading code. fun times lol
Re:Cafe Bench: Can LLMs run a coffee chain for a year?
on Wednesday September 23, 2026 @09:38AM (#49815993)
Author here, Life lately: build a hard eval → new model mogs it → build a harder eval → mogged again → repeat. Cafe Bench is the latest round this, it is a small eval ( world sim ) we built at Dot to test and track progress of the product.
But the data points transfer well into generalised model benchmakrs.
surprises: Opus 5.5 made +$227k for $8.57 in 22 minutes; GPT-6 Astra made +$157k but cost $56; and GPT-6 Luna lost $60k on average.
Cafe Bench: Can LLMs run a coffee chain for a year?
Show HN: Open source Chrome Extension to Auto-Create Google Tasks/Calendar
https://github.com/zodwick/lazel
hey hn,I built lazel because i wanted to get more organized, but was too lazy to do it myself. The extension is still under verification and not yet published, but i figured that it might be better to share as its fairly easy to set up locally and modify it to fit your needs.Right now it only supports Goggle Tasks and Google Calender, but the idea is to integrate more services.This is my fist...