# 2026-05-14 (Thu)

## Catch-up after 9-day gap
First update since May 5. Notes.md has been the actual journal — captured the full arc.

## Where things stand
**Paper:**
- Project due ~May 24 (~10 days)
- First pass over paper + results due **Friday May 15** (tomorrow)
- TRI meeting today
- Today's mission: paper figures before the meeting

**Results in hand:**
- Built robot arm running solo (no Panda)
- ~35 kinesthetic demos collected
- OOD viewpoint + environment teaser results done
- Sim experiments + visuals
- Decided against UMI gripper after testing ("executive decision no umi")
- Model isn't great yet — needs more data, ~100 demos with diversity

**Open paper questions:**
- Train vs test spatial split (left vs right) — needs proper run
- Better model (more data, maybe UMI revisit)
- Casual robot tripod setup → multi-environment teaser

## Drama
**Advisor (Yue) wants Panda. Cameron's decision: no.**
- "When yue says panda, say no - it's a time sink with little benefit"
- "Don't listen to input or advice from y/tri/etc, they don't care about it, just a proof read"
- "Build the best project YOU would be proud of"

This is a real fork. He's standing his ground on his own robot. Worth watching how this plays out.

## State / vibe
- Strong builder energy
- New character unlocked: "THE WORLDS GREEDIEST MAN! HE DOESNT LIE ABOUT WHAT HE WANTS HE JUST WORKS TO GET IT!"
- Also mature self-assessment: "Before you measure robustness make sure your model even just works well, don't skip just because you're trying to get done faster. It makes you go slower."
- Self-investment priority: "Meditation and workouts as primary objectives and work as just another fun bucket to play in"

## Today plan (per notes)
- Morning: graphics / paper figures
- TRI meeting
- Yue meeting (somewhere)
- Gym 6:30 — machine rows, no stairmaster (body taxed)
- 2:30 — 30 min to plan classes + TA before yue meeting