• [GitHub] Karpathy’s EPUB reader for vibe reading. Revelant tweet.

  • [Paper] On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes.

  • [Tweet] Grokipedia. AI-generated online wiki. Copies will be placed in orbit, the Moon and Mars.

  • [Tweet] Polymarket odds will be integrated into Google.

  • [Paper] Apparently, MLPs can learn in-context.

  • [Paper] Parallel generation as an alternative to long CoT chains.

  • [Blog] Signs of introspection in LLMs.

Have a great week!

Updated:

Comments

You May Also Enjoy

The week ahead: 20251201

[Blog] HOPE. A model as a set of nested sub-optimizers, each with its own context flow and hyperparams. Relevant paper.