Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take https://t.co/7V8Oxlfa2L
How to create a memo or deck for your startup by @gokulr
A great pitch is not hitting the right buzzwords or showing the right credentials
A great pitch is a strong conclusion that is supported by uncontroversial, logical, achievable statements that require no magical thinking https://t.co/sIHzgrlkUn