Reinforcement Learning from Human Feedback (RLHF) is a method where AI models are fine-tuned using data from human interactions. It empowers systems to understand human preferences better, as seen in videos about fine-tuning models like Claude and optimising agents like Unitree G1. You'll learn how RLHF shapes AI systems, addresses issues like reward hacking, and drives advancements in reasoning models, making it essential for AI engineers and enthusiasts.
14:41
16:19
10:44
26:00
43:29
51:57
15:06
14:25
47:54
Your idea can be anything. At our last workshops, people built plant-based nutrition businesses, a way to measure planetary resilience, crochet headwear and a way to connect lonely people living in the same building. An asset manager went on to raise an additional £25M on their fund within nine months. The fourth workshop is a full day at KOKO with Nick Sarafa, learning to build with Claude Code. Bring the thing you keep meaning to start. We’ll bring the pizza.
Apply once › get screened › meet the company
16:31
12:41
20:37
08:38
28:40
38:02
24:50
07:43
22:43
11:29
17:36
34:50
28:53
33:18
Let us build it for you. Design and engineering from the people who shipped platforms to billions of users. AI-native, live in weeks, and yours outright at the end.
One a week, never sold on, and one click to stop.
We use a few cookies to keep the site running. Necessary ones are always on. Analytics + marketing are off until you say otherwise.
Read our cookie policy · privacy.