Skild's S1: robots leave the BERT era — one video prompt, zero fine-tuning
deepakpathak · x · 2026-08-26
Skild AI founder Deepak Pathak introduces S1: in-context learning for robotics via the official blog. Core thesisLanguage modeling offers a blueprint: BERT-style models needed data collection plus fine-tuning per application, while ChatGPT's pivotal leap was in-context learning — injecting new concepts via prompt without touching weights. Robotics remains stuck in the BERT era: robust new-task execution still demands tens to hundreds of hours of post-training data in deployment conditions, and research (Oh et al., 2026) shows that with sufficiently dense post-training data, from-scratch policies match post-trained foundation models — so what is pre-training for?S1 capabilities- Unseen tasks never in pre-training - 10-minute horizons - Single video prompt, no post-trainingResponding to skeptics, Pathak likens it to a natural extension of system prompts as in Claude/GPT, and notes the blog shows the robot generalizes quite far beyond the prompt. He also teases more real user cases and, eventually, home robots.
More from Embodied
- First Robot Fight Betting Event: 200lb T800 Championship — zealcaiden · 2026-08-26
- SF robotics company builds custom mic array for better AI interaction — Scobleizer · 2026-08-26
- Opinion: Robotics ICL needs public access for a 'GPT-3 moment' — chris_j_paxton · 2026-08-26
- MIT professor explains why AI still can't load the dishwasher — vincesitzmann · 2026-08-26
- Q-Planning boosts robot self-improvement from 25% to 80% success — chris_j_paxton · 2026-08-26
- Max Welling: Why the Next AI Breakthrough May Come from Physics — TWIML AI Podcast · 2026-08-26