Magic sizes enable high-fidelity assembly of programmable shells
(news.ycombinator.com)
91.
92.
Why can't transformers learn multiplication?
(news.ycombinator.com)
93.
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
(news.ycombinator.com)
94.
Fast-DLLM: Training-Free Acceleration of Diffusion LLM
(news.ycombinator.com)
95.
Antislop: A framework for eliminating repetitive patterns in language models
(news.ycombinator.com)
96.
Antislop: A Framework for Eliminating Repetitive Patterns in Language Models
(news.ycombinator.com)
97.
Secret diplomatic message deciphered after 350 years
(news.ycombinator.com)
98.
Llama-Factory: Unified, Efficient Fine-Tuning for 100 Open LLMs
(news.ycombinator.com)
99.
100.
Techno-feudalism and the rise of AGI: A future without economic rights?
(news.ycombinator.com)
101.
Techno-Feudalism and the Rise of AGI: A Future Without Economic Rights?
(news.ycombinator.com)
102.
Extracting memorized pieces of books from open-weight language models
(news.ycombinator.com)
103.
104.
Geometry from Quantum Temporal Correlations
(news.ycombinator.com)