Chelsea Finn @chelseabfinn · 16 Apr 2026
LLM post-training used to mean fine-tuning to a downstream task Robotics has been stuck in this setting, needing task-specific fine-tuning for best performance π07 changes this: It works out of the box & outperforms fine-tuned specialists Details: https://t.co/QbO3E4D3QN https://t.co/B6nDO7gnWn
72 318Views
616Likes
64Reposts
28Replies
13Quotes
223Bookmarks
Is that a lot?
1.04×vs this author's median69 350 views is typical
57Percentile for this authorof 7 recent posts
3.26×vs 100K–1M median22 159 views is typical
71.38%Reachviews ÷ followers
1.00%Engagement rateof viewers reacted