You all know how big of a fan of @cline I am. After using it obsessively and telling everyone I could about Cline, recently, I was lucky enough to be asked to invest. Of course I said yes. Thrilled to support the @sdrzn @nickbaumann_ + team through their next phase of growth!
@mattshumer_
-
Improving AI Model Training with Enhanced Scaling Approaches
By
–
Good catch! This likely would be fixed with more robust training (more steps + rollouts, and ideally a larger than 1.5B model) 🙂 This was mostly just to show how it works. Feel free to try the same task with a larger model, more steps etc.
-
RL Model Training Made Accessible for Developers
By
–
You literally can’t be too lazy to train a model with RL with this approach No excuses anymore Go build!
-
LoRA Training Preserves Base Model Context Window
By
–
It's just training a very small LoRA you can merge back into the base model, so it should retain the context window!
-
RULER enables new prompts and capabilities for AI models
By
–
I just had an idea and added a few prompts. RULER was the big reason this was possible!
-
Self-improving AI systems and automatic task generation
By
–
It's not quite *self*-improving, as it still requires the user to describe the task, but of course, yeah, in theory, the system could also auto-generate tasks.
-
Single-turn to multi-turn generation expansion announced
By
–
Right now, single-turn tasks only, but I will very likely expand this to multi-turn generation soon!
-
Building AI Systems with Open-Source Models Only
By
–
Yep! You can even do it entirely w/o any closed-source models in the loop! In the demo above, it was powered entirely by Kimi, Deepseek, and Qwen.
-
Training AI Models for Under One Dollar Now Possible
By
–
Yep! And you can train a model for literally $1 or less
-
Vibe Training Replaces Vibe Coding in AI Development
By
–
Forget vibe coding. Vibe *training* is now a thing.