Baseten training co-head and Engram Lab founder debate continual learning over a HORSE game
baseten · x · 2026-10-13
Baseten released a lighthearted technical conversation: co-head of training Claire O'Neill and Engram Lab co-founder/head of research jxmnop debate continual learning between HORSE basketball shots, covering:
- when to put knowledge in weights vs. the KV cache
- why forgetting matters less for specialized models
- on-policy self-distillation vs. RL
- what research publishing should look like today
Full video available.
More from Research
- Base Labs investigates why models forget facts they iteratively learn, with 13B talkie — baseten · 2026-10-13
- Robot deployment is becoming the operating layer for post-training physical AI policies — paigeinsf · 2026-10-13
- New J++ Lens interpretability method delivers 55% more faithful readouts than J-Lens — wesg52 · 2026-10-13
- Spatial biology slide costs stuck at $5-10k for five years, defying Moore's law — anshulkundaje · 2026-10-13
- Google Research trains user simulators with latent intrinsic feedback, cutting RL compute by over half — cocoweixu · 2026-10-13
- Helmholtz-SDE closes the approximation gap in simulation-free latent SDEs — scott_linderman · 2026-10-13