I write (sparsely) at: vivekkalyan.com
I explore the idea of spending more compute for RAG systems to significantly improve performance.
www.vivekkalyan.com/writing/scal...
I explore the idea of spending more compute for RAG systems to significantly improve performance.
www.vivekkalyan.com/writing/scal...
We trained 2 new models. Like BERT, but modern. ModernBERT.
Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.
It's much faster, more accurate, longer context, and more useful. 🧵
See some demos of open-source repos here (no sign-up required):
cartograph.app/demo
(Reply here if you'd like to see others added)
See some demos of open-source repos here (no sign-up required):
cartograph.app/demo
(Reply here if you'd like to see others added)
github.com/vivekkalyan/...
github.com/vivekkalyan/...
github.com/vivekkalyan/...
## Building AI systems
• Patterns for Building LLM-based Systems: eugeneyan.com/writing/llm-...
• What We’ve Learned From A Year of Building with LLMs: applied-llms.org
LLMs are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?
arxiv.org/abs/2411.12946
This requires some technical know-how for now, but I'm hoping that we see some no-code solutions for this pop up soon, like Ghost or Wordpress plugins.
emilyliu.me/blog/comments
Paper: allenai.org/papers/tulu-...
Demo: playground.allenai.org
Code: github.com/allenai/open...
Eval: github.com/allenai/olmes
Notes
Paper: allenai.org/papers/tulu-...
Demo: playground.allenai.org
Code: github.com/allenai/open...
Eval: github.com/allenai/olmes
Notes