Remember when we were copying codes from chat interfaces into text editors and running commands by hand that was less than 2 years ago btw
@theahmadosman
-
Codex CLI tip: restart session when KV cache slows tokens/sec
By
–
PRO TIP Once Codex Cli becomes too slow, start a new session Something is broken (potentially KV Cache handling) and it is harming the tokens/sec performance
-
Unified Memory and the Future of Local AI
By
–
One thing I discounted was that Unified Memory might actually play very well for small and efficient models We'll see how it goes, but the future of Local AI is bright and that's the most important thing
-
NVIDIA and Microsoft launch accelerates local AI mass adoption
By
–
NVIDIA and Microsoft are killing it with their launch today We're accelerating and going into the Local AI mass adoption stages
-
Local AI entering mass adoption stage
By
–
Local AI is going into its mass adoption stage finally! Love seeing it!
-
GLM 5.3 Flash vs DeepSeek V4.1 Flash model comparison
By
–
GLM 5.3 Flash > DeepSeek V4.1 Flash for coding DeepSeek V4.1 Flash > GLM 5.3 Flash for visual tasks
-
Reflection on training a small model on Bash commands
By
–
Oh how far we’ve come Nobody back then was doing anything genetic while I was trying to train a small model on Bash commands Stuff like this made me fall in love with AI and make so many right calls early on I just love this shit tbh
-
Much left to build in the Local AI Stack
By
–
You guys have no idea but there’s so much left to build in the Local AI Stack
-
Advocating for Local AI as the Default
By
–
We’re just getting started and we’re not gonna stop until Local AI is the default 🫡
-
One-click Hermes deployment for local AI via ODS
By
–
You want Hermes? We got you Hermes with one click Everything in one place, the best and most seamless experience for Local AI today is ODS without a doubt