I just had an idea and added a few prompts. RULER was the big reason this was possible!
@mattshumer_
-
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.
-
OpenRouter Credits Enable Cost-Effective AI Model Execution
By
–
For this run, I spent $0 on the GPU, and 40 cents on OpenRouter credits for prompt generation, RULER ranking, etc.
-
Fast AI Model Training System Delivers Impressive Grammar Results
By
–
It's incredible how quickly you can go from an idea to a fully-trained model with this system. And the resulting models are really good! The grammar model in the demo video works really well, yet it was trained for just minutes, and was only 1.5B params 🙂
-
OpenPipe’s RULER Enables LLM Training Without Labeled Data
By
–
Under the hood, this is powered by @OpenPipeAI
's ART library. Their RULER technique made this possible, as it doesn't require labeled output data. With no need for labeled outputs, we can just sample a LLM to generate scenarios to RL against. Absolutely crazy!