arXiv:2611.22055v1 Announce Type: new
Abstract: Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space programming, a large language model (LLM) writes target weights by hand without gradient-based training, so those reasons no longer apply. Should we keep the Transformer? Given minimal guidance, ten labeled examples, and a sandbox, mainly on multiple-choice questions, we task three frontier LLMs with either generating the weights of a fixed architecture or designing the architecture themselves. When free to design, all three compile plain-text facts into a sparse table queried by a fixed procedure, reaching up to 54.4% test accuracy. An LLM-designed model achieves higher test accuracy than the most accurate released Transformer that the same LLM wrote while using about 1,800x fewer parameters. Without gradients, they choose a table, in which the LLM can state what each weight means and can find and rewrite a wrong one. Each wrong answer points to one row, and removing a row changes about one other answer. From this, we propose an associative-memory-based model up to 17x faster on GPUs than a same-sized Transformer. We also test pretrained weights, other benchmarks, and tasks where models generate answers. Pretrained LLMs remain more accurate; the claim concerns which structure to build when writing weights.
Trending
- [2611.25514] Sequential Probability Assignment against Smoothed Adversaries with Unknown Base Measure
- Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch
- WeightCode: Installing New Capabilities into Neural Networks via Weight-Space Programming
- On-Policy Distillation for Few-Step Flow-Map Generators
- Dimension-Free Buffer Bounds for Compressed-Momentum Error Feedback
- New in AWS Quick: More capable flows, an updated web experience, and agents that work together
- A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training
- CTO of ‘RansomwareHelp’ Indicted for Wire Fraud – Krebs on Security
