Smart Brevity podcast

Smart Brevity 7: Score the net, not the gross: memory, training data, and benchmarks judged against the plain baseline

31/10/2026
0:00
8:25
Reculer de 15 secondes
Avancer de 15 secondes
Score the net, not the gross: memory, training data, and benchmarks judged against the plain baseline; Memory tax: agent memory must beat naive RAG over raw history, and often does not.; Benchmarks as difficulty measures: measure mismatch and coverage gaps hide what a score really says.; Decision grounding: train only on actions the agent could justify from what it saw.; Turn-level credit assignment: agents decide in turns, so RL should assign credit per turn.; Interface lock-in: fine-tuning one answer format improves only that readout.; Decision models as routing economics: send yes/no agent steps to cheap typed-answer models.; In-situ interventions: a few dozen examples

D'autres épisodes de "Smart Brevity"