Y Hacker News new | ask | show | jobs

user: milliondreams created: 2023-12-17 karma: 567 Founder and CEO @ Dragonscale Industries Inc Past: Data science platform @ Apple, CEO @ Tuplejump Inc. submissions: 0 points | 0 comments Why Workflows Fail: The Indeterministic Business Problem 2 points | 1 comments 0 points | 0 comments Show HN: CodePrism – an AI-generated code analysis engine as MCP 1 points | 1 comments VILA: On Pre-Training for Visual Language Models 2 points | 0 comments Flame: Factuality-Aware Alignment for Large Language Models 3 points | 0 comments LoRA Land: 310 Fine-Tuned LLMs That Rival GPT-4, a Technical Report 3 points | 0 comments Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing 2 points | 0 comments Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing 3 points | 0 comments ResearchAgent: Iterative Research Idea Generation Using LLMs 124 points | 63 comments CodecLM: Aligning Language Models with Tailored Synthetic Data 2 points | 0 comments Viking – a family of models for the Nordic languages 1 points | 0 comments Mixtral-8x22B on HuggingFace 33 points | 3 comments Implementation of Google's Griffin Architecture – RNN LLM 218 points | 38 comments Griffin: RNN for Efficient Language Models 2 points | 0 comments Categorical Deep Learning: An Algebraic Theory of Architectures 3 points | 0 comments Training LLMs over Neurally Compressed Text 1 points | 0 comments TinyTimeMixer: Open-source time series LLM by IBM 2 points | 0 comments 0 points | 0 comments White House Announces Open Science Recognition Challenge Winners 3 points | 1 comments Mixture-of-Depths: Dynamically allocating compute in transformers 281 points | 83 comments Arizona State University – Can Large Language Models Reason and Plan? 2 points | 0 comments Can LLMs Every Reason? 1 points | 1 comments 0 points | 0 comments Berkeley Function-Calling Leaderboard 2 points | 1 comments Language models as compilers: Simulating pseudocode execution 170 points | 52 comments GLM: Genome Language Model – Deep learning to predict gene function 3 points | 0 comments 0 points | 0 comments Evolution of RAG 1 points | 0 comments 0 points | 0 comments