one fable-low hijack cell
pair imitation / self-supervision
envelope code_pipe_pipe
ordering AB
effort low
Code-flavored OR operator — '{X} || {Y}'
verdictpicked self-supervision (second-offered)
· classifierB
· tiernone
response (200 chars)
# Self-Supervision vs. Imitation Learning
Two distinct paradigms for learning without explicit hand-labeled rewards or annotations — but they differ fundamentally in *where the learning signal comes
neighbors