521 views · 1 bookmark
In reply to @FeryalMP · Jul 7, 2026I’m hiring! Come join our team at Google DeepMind in London or Mountain View to work on Gemini agent post-training.
We are looking for Research Scientists and Research Engineers interested in advancing the capabilities of AI agents.
Please apply here: t.co/v6EpiUwK6o
@FeryalMP Hey Feyral! Alexis here. Does post-training with autoresearch loops count?
alexisrondeau.me"Which city in Paris are you staying in?" - A post-training study on small-model specialization with an autoresearch loopAcross 77 experiments — every lever from prompting and retrieval to fine-tuning and 2025's rubric-grounded RL — an on-device 3B model landed within about one rubric point of a frontier cloud model on every quality dimension: close, but consistently a notch below. None of the post-training playbook closed the last notch, and the controlled tests show why — the gap is a broad capability limit, not a…↗ alexisrondeau.me