MindPatternSubscribe

Source trail

mnoukhov.github.io (Michael Noukhovitch)

Public MindPattern findings, entities, and graph evidence that cite this source.

Findings

1

All-time hits

1

High value

0

Last seen

2026-09-16

Related findings

2026-09-16 / VOICESNever Give Up: a fix for the Matthew Effect in RL, where training keeps improving problems the model already solvesMichael Noukhovitch published NGU on September 15 (submitted to HN by Nathan Lambert), naming the failure mode as the Matthew Effect: standard GRPO concentrates compute on easy problems while hard ones stagnate, and a scalar average hides it. NGU starts with small completion counts and re-queues unsolved problems with probability p, producing a geometric distribution of attempts weighted toward the hard cases. On GSM8k, k=4 with p=0.9 beat every standard GRPO configuration on the hardest subsets; on DeepScaler with Qwen 3 4B base (~120 H100 hours) it improved AIME 2025 and BRUMO 2025 without regressing easy problems. The transferable lesson for anyone running RL or evals is to read fine-grained per-difficulty metrics rather than a single average.

Open latest cited source