Proud to share that I implemented the PPO agent in the Dopamine library! It was an amazing experience working with Pablo Samuel Castro during my internship at Google DeepMind! Check it out here: github.com/google/dopamine

In the US, an average of 37 deaths per year are related to heatstroke in kids. That’s why we developed Cabin Radar – a 4D imaging sensor that requires little power & can detect respiration through organic non-metallic occlusions (such as car seats). Cabin Radar first row

Thrilled to be part of the team behind Snorkel Expert DaaS — expert-quality AI datasets powering the next generation of frontier LLMs 🚀

Check out our Expert Data Leaderboard: leaderboard.snorkel.ai

Parsing isn't neutral. At Snorkel AI, we show how extraction choices shape AI evaluation results. Check out my blog! snorkel.ai/blog/parsing-i…

Excited to share a new paper I co-authored with the Snorkel Research team: BeTaL — Benchmark Tuning with an LLM-in-the-loop. We explore how LLMs can reason about and refine benchmarks—creating dynamic evaluations that evolve with model capabilities. 📄 arxiv.org/abs/2510.25039

🚨 New research from Snorkel AI tackles a critical problem: LLMs are evolving faster than our ability to evaluate them 📊 We develop BeTaL— Benchmark Tuning with an LLM-in-the-loop— a framework that automates benchmark design using reasoning models as optimizers. BeTaL produces

Today, we’re announcing the next chapter of Terminal-Bench with two releases: 1. Harbor, a new package for running sandboxed agent rollouts at scale 2. Terminal-Bench 2.0, a harder version of Terminal-Bench with increased verification

Proud to be part of the community behind #TerminalBench 2.0 — a benchmark of realistic terminal-based tasks for evaluating agentic systems. Laude Institute Stanford University

Heading to NeurIPS next week! If you'll be there and want to connect, feel free to DM me.

I’ll be at #NeurIPS2025 (12/3-12/8) representing SprocketLab at UW–Madison Computer Sciences and Snorkel AI. If you’re coming and want to chat about data-centric AI, data development, agents, or foundation models, reach out!

Part 5 of the Snorkel rubrics series is live. We dive into the future of agentic, multimodal, tool-using AI and the alignment power of dynamic rubrics. Full blog here: snorkel.ai/blog/part-v-fu…