Preface to the Computational Agent Theory and ASI Alignment Sequence

A researcher analyzed logits from open models to measure their random number generation predictability by calculating bits of entropy and guesses-to-crack metrics.

Researchers introduce Latent Compaction, a test-time training method that compresses KV caches 32× while maintaining 96.7% accuracy on retrieval tasks.

Researchers introduce a retraining-free method to make transformers elastic, enabling on-the-fly adaptation across computational budgets by jointly ranking MLP neurons and attention heads.

Researchers introduce a new generative representation learning approach for scalable latent tokenization that achieves compute-optimal improvements over direct diffusion methods.

Researchers prove first-price auctions in AI agent markets can achieve near-optimal welfare under competitive floors and conditional independence assumptions.