Artificial Intelligences, So Far – by Kevin Kelly – KK

The scientists who invented the current crop of LLMs were trying to make language translation software. They were completely surprised that bits of reasoning also emerged from the translation algorithms. This emergent intelligence was a beautiful unintended byproduct...

How to scale RL – by Nathan Lambert – Interconnects

“Scaling reinforcement learning (RL)” is the zeitgeisty way to capture the next steps in improving frontier models — everyone is staring at the same hill they plan on climbing. How these different groups are approaching the problem has been a poorly kept secret. It’s...

Inference.net Blog | Agentic Search

RL takes search agents to the next level. Without RL, agentic search is powerful but slow; you often need expensive frontier models to get the best results. With RL, it becomes much more viable. Go to Source