Tinker
Software / App
An open-source library from Thinking Machines that uses Rank One LoRA for fine-tuning and RL, mentioned as an alternative to steering for model adaptation.
Mentioned in 2 videos
Save the 2 videos on Tinker to your own pod.
Sign up free to keep building your knowledge base on Tinker as more episodes are added.
Videos Mentioning Tinker
Goodfire AI’s Bet: Interpretability as the Next Frontier of Model Design — Myra Deng & Mark Bissell
Latent Space
An open-source library from Thinking Machines that uses Rank One LoRA for fine-tuning and RL, mentioned as an alternative to steering for model adaptation.
AI Dev 26 x SF | Diamond Bishop: The Next 100 Agents. Building the Agent Native Office
DeepLearningAI
A startup mentioned in the context of reinforcement learning for enterprise.