30
42
30
30
57
57
57
30
57
30
57
57
57
Magnitude exploit kit
60
30
55
60
30
55
57
35
57
57
57
57
30
30
60
60
55
42
60
Why don't machine learning research agents overfit?
Amazon researchers explain why ML research agents avoid benchmark overfitting, attributing generalization to compressibility of successful strategies.
Amazon Science summarizes the paper "What fits (into few tokens) doesn't overfit: Compression and generalization in ML research agents," which investigates why benchmark hill-climbing loops, whether run by human communities or LLM research agents, do not produce rampant overfitting. The explanation formalizes Occam's razor via a counting argument: successful ML strategies are highly compressible, so short descriptions lack room to memorize benchmark data and must capture real structure. LLM-based agents, being resettable and controllable, allow this hypothesis to be tested empirically.
Hacker News · security32
30
60
30
57
30
60
30