As long as a LLM doesn’t run into a corner, making the same mistakes over and over again, it is magical to just paste some code, ask what’s wrong with it and receiving a detailed explanation + fix. Even better is when you ask “now can you add this and this to it?” and it does.

Same for me. Right now I don’t need a laptop at all but when I get one, it will be a framework.

Revolt isn’t federated, every instance is standalone.

Haven’t tried bard but use ChatGPT to write/debug scripts and SAP stuff. Also asking it when I have simple but technical questions.

I am also downloading and running the latest models in the local LLM space every 2-3 weeks, just waiting for the point at which they finally take over gpt3.5 at which point I’ll probably not touch ChatGPT again.

Also, we will probably have language models running locally on our phones with all the info we’ll ever need in a short few years anyways.

The video in that article is hilarious.

The lobotomies will continue. Free models will keep getting better.

Feature, not a bug <3

Yunohost is awesome, if only for the dyndns. I try to host most of the stuff in docker but dyndns never quite worked for me unless it was the yunohost one.

Firefox > Chrome

Perhaps some billionaire would adopt you and make a game out of defending you :P

Lmao me too.

Sounds like it would get filled up with overwhelming amounts of crap pretty quickly and on the server-side, refreshing a huge number of feeds would take a lot of resources.

Ublock + Sponsorblock are a killer combo I couldn’t use the internet without. I also use keepa to see amazon price history.

https://gdpr.eu/right-to-erasure-request-form/ <3