A lot of my working life over the past year has been preoccupied with harness engineering. When @HamelHusain introduced me to @doesdatmaksense to chat about how evals belong at the center of harness engineering, I immediately wanted her to write a guest post for the VG substack. Check it out to take your agent evals to the next level: Thanks, AS & HH!

Welcome to the revenge of the data scientist! People spent the past few years declaring data science dead. Then we started building products around agents that generate more data, noisier signals and plausible-looking outputs nobody knows whether to trust. Someone has to reason about all of that, debug it and work out whether the system is actually working. And guess what... that’s data science! I’ve taken @HamelHusain and @sh_reya's AI Evals for Engineers & PMs course several times now. They’ve rebuilt the whole thing from scratch for the age of agents, so apparently I’m going back again 🤣 The new cohort starts today. Hamel and Shreya have very kindly given the Vanishing Gradients community 25% off: Come learn with me!

just had a wild and high signal chat with @HamelHusain about the current state of agentic AI, evals, data science, and the rise of the AI scientist. a few things we discussed 👇 full chat here:

chatting with @HamelHusain tomorrow about * why "it's hard to eval" is a product smell * how agents have changed the eval landscape and how @sh_reya and he have updated their course * whether data science is dead in the age of AI agents or not ​Register to join live or get the recording afterwards:

Next week I’m sitting down with @rasbt, independent AI researcher, author of Build a Large Language Model (From Scratch) and Build a Reasoning Model (From Scratch), and creator of Ahead of AI, which just crossed 200,000 subscribers. Since we last spoke, Sebastian and I have been messaging about the insanity of DeepSeek-V4, then GLM-5.2, and now Kimi K3. Qwen3.8 is about to land as well. I’m excited to ask him: • What are these new models actually doing differently? • What do stronger open-weight models mean for local coding agents? • Which parts of our agent systems will survive the next model release? • What did he learn by starting with a small Qwen3 model and adding evaluation, inference-time scaling, reinforcement learning, and distillation himself? What do you want me to ask Sebastian? Reply with your questions and I’ll ask my favourites live. @ManningBooks is giving away five ebook copies of Sebastian’s new book to the people who ask the best questions. They’re also providing a 45% discount for the audience. We’re live July 28. Registration link below.