Stefania Druga

Memory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.ai

Aug 12, 2026 · 13:04

Stefania Druga, a research scientist at Sakana AI in Tokyo, presents experiments on memory harnesses for long-running research agents running on local models like Qwen 27B and DeepSeek V4 Flash on an M3 Ultra. She frames memory as a write-manage-read control loop, not a database, and tests a recall ladder—no recall, vector RAG, a ranked decisions ledger, and an oracle—across 68 xbench questions. The ranked ledger performed best, beating even gating on whether memory is needed, while the oracle didn't hit max because giving the right memory doesn't force its use. When tasks fit in context, memory only added cost with no accuracy gain, but for long-horizon tasks where answers sit far outside the window, good recall policy became essential and cheaper. She urges treating recall policy as a first-class metric and highlights the broader memory technique landscape, including over 30 runnable cookbooks from Diamond, while noting local models run serially, which is why her Tokyo machine…

Real-time Experiments with an AI Co-Scientist - Stefania Druga, fmr. Google Deepmind

Jul 28, 2025 · 18:42

Stefania Druga, formerly at Google DeepMind, demonstrates a real-time AI co-scientist system built with under $300 in open-source hardware and two weeks of effort, capable of live scientific experimentation. Using a micro:bit with Jack DAC temperature sensor, ReCamera for object tracking, and a microscope, the system streams sensor data, images, and voice to Gemini via a React app that dynamically assembles multimodal context. Druga presents two home experiments: crystal growth, where she discovered that formation occurs in bursts once critical saturation is reached, and fermentation, monitoring CO2 and temperature to optimize dough rise. She references DeepMind's AI co-scientist paper, which replicated a 12-year gene transfer discovery in two days and identified novel drug targets for liver fibrosis that proved effective in wet labs. Her vision moves from async data analysis to real-time empirical hypothesis generation, and she highlights open-source platforms like Jubilee and open bioreactors for automating lab equipment, with future plans to use real-time data to inform realistic simulations.

AI Engineers: The Next Generation — Stefania Druga, Google Gemini

Apr 13, 2025 · 21:47

Stefania Druga, a research scientist on Google Gemini, presents Cognimates and its new AI copilot that teaches children to become AI engineers. Built on Scratch’s visual programming, Cognimates lets kids train custom models, program robots, and build games, shifting their perception from ‘AI is magic’ to understanding data and confidence levels. Druga’s design studies with 18 kids from 11 countries showed the copilot doubled programming time by supporting ideation, debugging, and creative agency—never giving answers unless stuck three times. The tool now integrates screenshot analysis and asset generation, with plans to embed the agent across the OS. Druga ties this to the EU AI Act’s mandate for AI literacy, arguing early, hands-on creation is the path to informed users.

The Multimodal Future of Education: Stefania Druga

Oct 24, 2024 · 20:05

Stefania Druga, a research scientist on Google's Gemini team, argues that multimodal AI can transform education by making learning more interactive and critical. She presents Cognimates, an open-source platform she built that expands Scratch to let kids train custom AI models and program smart devices, showing a longitudinal study where kids became more skeptical of AI's intelligence after tinkering. Druga also introduces a benchmark for math misconceptions and demonstrates live demos using the Gemini API—a science tutor that responds to drawings, a math coach that avoids giving direct answers, and a curiosity-driven object identifier—all in under 100 lines of code. She emphasizes the need to cultivate AI literacy early, as 70% of generative AI users are Gen Z, and invites engineers to build tinkering tools that balance agency between learners and AI.