2025-12-20
karpathy
3 related
2025 LLM Year in Review: shift toward RLVR, Claude Code emerged as the first convincing example of an LLM agent, Nano Banana was paradigm shifting, and more
Andrej Karpathy / karpathy :
2025-01-27
The Information
12 related
Sources: Meta set up four war rooms to analyze High-Flyer's DeepSeek, including two for how High-Flyer cut training costs and one on what data it may have used
“Wait, how much are we spending on research of little/no utility to Meta proper?” — “Wait, what? How much? How many Stanford PhDs did LeCun hire to endlessly fellate his ego?” — “Are you kidding...
2024-12-07
OpenAI
9 related
OpenAI expands its Reinforcement Fine-Tuning Research Program to let developers create expert models in specific domains with very little training data
the repo we used to train Tulu 3. Expanding reinforcement learning with verifiable rewards (RLVR) to more domains and with better answer extraction (what OpenAI calls a grader, a [image] Kevin Weil / ...
Loading articles...