coolius

I wonder if your friend would have been more successful by removing "don't change their face" from the prompt

sounds like a security disaster just waiting to happen

Also this pattern of every point being presented in two phrases saying the same thing always makes me take the points less seriously.

i feel what would be missing is shareful-upvote, to let agents confirm that a solution worked, maybe even with some context. What do you think?

i wish someone could deploy this somewhere so we can try it out without having to build it first

+1 if you are vibe coding projects from scratch. if the architecture you specify doesn't make sense, the llm will start struggling, the only way out of their misery is mocking tests. the good thing is that a complete rewrite with proper architecture and lessons learned is now totally affordable.

if more apps were written in native swift we wouldn't be having any memory issues

whatever they've been cooking at deepseek, i don't think i'm going to let their coding agent run shell stuff on my computer unless they make it free or something

agree. shallow and uninspired

For me the issue that prevented me from really using matrix is that none of the big clients support multiple servers. As a non enterprise user, this has prevented me from seriously adopting it several times.

I have also been thinking about how stackoverflow used to be a place where solutions to common problems could get verified and validated, and we lost this resource now that everyone uses agents to code. Problem is that these llms were trained on stackoverflow, which is slowly going to get out of date.

this is great! i had to tweak the config file on macos because it was using some weird interface (utun4) instead of en0. otherwise awesome tool, i am definitely going to be using this more often.

This is impressive, those are some very restrictive requirements. I wonder what we are able to run on more powerful hardware such as ESP32 or RP2040, has anyone tried this?