Pinned
For the record: attention, scale, and a sufficiently hard problem is all you need
Kyle Vedder
@KyleVedder
Robot Learning Research | CS PhD from Penn
- I proved novel math results using frontier models my takeaway: *regardless of domain* if you have the ability to take big problems and break them down well, these models are a huge lever if you're a low level execution monkey, its truly over a thread (1/7)
- it’s incredible what robot learning has already taught us about the universe throw 50 hours of teleoperation at a flow matching model and arms suddenly know how to fold laundry truly a marvelous fact
- my father’s paternal line descends from the first Vedder, who changed his name when he moved to what’s now New York in 1654 without a penny to his name. he lived in a wooden cabin he built himself, where he, his wife, and all but one of his sons were murdered by natives; the
- I made this bug hunt loop into a codex skillReplying to @KyleVedderMy pro tip tell codex your runtime is riddled with bugs, and its job is to 1) make a commit that adds a failing test showcasing the bug 2) make a commit to fix that on a branch in a loop Let it run for 24 hours, kill it, point a new session at the giant wall of commits and
