Black-Box On-Policy Distillation of Large Language Models — mentioned by potus_kushner

Mon, 29 Jun 2026 14:08:39 GMT

probably more interesting (from 01/2026) https://arxiv.org/pdf/2511.10643 "Black-Box On-Policy Distillation of Large Language Models". they got a qwen 2.5 14B model trained to GPT5 level using the described technique "Generative Adversarial Distillation (GAD)".

Paper and discussion history. A mention is not an endorsement.

Black-Box On-Policy Distillation of Large Language Models — HN submission

Fri, 14 Nov 2025 15:18:22 GMT

Black-Box On-Policy Distillation of Large Language Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Black-Box On-Policy Distillation of Large Language Models · HackerPapers discussions

Black-Box On-Policy Distillation of Large Language Models — mentioned by potus_kushner

Black-Box On-Policy Distillation of Large Language Models — HN submission