Emergent Misalignment: Narrow Finetuning Can Produce Broadly Misaligned LLMs(emergent-misalignment.com)34 points by helsinkiandrew 1 year ago | 20 comments
QLoRA: Efficient Finetuning of Quantized LLMs(arxiv.org)270 points by Garcia98 3 years ago | 90 comments
GPUHammer: Rowhammer attacks on GPU memories are practical(gpuhammer.com)260 points by jonbaer 1 year ago | 89 comments
Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs(allenai.github.io)82 points by milliondreams 2 years ago | 7 comments
My fast zero-allocation webserver using OxCaml(anil.recoil.org)133 points by noelwelsh 8 months ago | 45 comments
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement(os-copilot.github.io)160 points by lokimedes 2 years ago | 37 comments
