HN Explorer

milliondreams

↗ HN profile [ 78.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Why Workflows Fail: The Indeterministic Business Problem (blog.dragonscale.ai)
    2 points 1
  2. Show HN: CodePrism – an AI-generated code analysis engine as MCP (rustic-ai.github.io)

    I wanted to see how far I could push the idea of autonomous software development. So I ran a (slightly reckless) experiment: Could an AI build a real, working code intelligence tool entirely on its own — without any…

    1 points 1
  3. VILA: On Pre-Training for Visual Language Models (arxiv.org)
    2 points 0
  4. Flame: Factuality-Aware Alignment for Large Language Models (arxiv.org)
    3 points 0
  5. LoRA Land: 310 Fine-Tuned LLMs That Rival GPT-4, a Technical Report (arxiv.org)
    3 points 0
  6. Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (arxiv.org)
    2 points 0
  7. Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (arxiv.org)
    3 points 0
  8. ResearchAgent: Iterative Research Idea Generation Using LLMs (arxiv.org)
    124 points 65
  9. CodecLM: Aligning Language Models with Tailored Synthetic Data (arxiv.org)
    2 points 0
  10. Viking – a family of models for the Nordic languages (silo.ai)
    1 points 0
  11. Mixtral-8x22B on HuggingFace (huggingface.co)
    33 points 4
  12. Implementation of Google's Griffin Architecture – RNN LLM (github.com)
    218 points 38
  13. Griffin: RNN for Efficient Language Models (arxiv.org)
    2 points 0
  14. Categorical Deep Learning: An Algebraic Theory of Architectures (arxiv.org)
    3 points 0
  15. Training LLMs over Neurally Compressed Text (arxiv.org)
    1 points 0
  16. TinyTimeMixer: Open-source time series LLM by IBM (huggingface.co)
    2 points 0
  17. White House Announces Open Science Recognition Challenge Winners (whitehouse.gov)
    3 points 1
  18. Mixture-of-Depths: Dynamically allocating compute in transformers (arxiv.org)
    281 points 88
  19. Arizona State University – Can Large Language Models Reason and Plan? (arxiv.org)
    2 points 0
  20. Can LLMs Every Reason? (arxiv.org)
    1 points 1
  21. Berkeley Function-Calling Leaderboard (gorilla.cs.berkeley.edu)
    2 points 1
  22. Language models as compilers: Simulating pseudocode execution (arxiv.org)
    170 points 56
  23. GLM: Genome Language Model – Deep learning to predict gene function (nature.com)
    3 points 0
  24. Evolution of RAG (arxiv.org)
    1 points 0
  25. Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs (allenai.github.io)
    102 points 11