HN Explorer

codelion

↗ HN profile [ 1432 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Cross-Lingual Alignment Without Joint Training (arxiv.org)
    1 points 0
  2. Voice AI Benchmarks: a directory of voice-agent evaluations (voicebenchmarks.com)
    1 points 0
  3. Neural Canvas: a fruit fly connectome demo in the browser (huggingface.co)
    1 points 0
  4. Iris: Climbing to the Search Frontier (arxiv.org)
    1 points 0
  5. The Recursive Economy: AI Self-Improvement and Scarcity (recursive-economy.pages.dev)
    1 points 0
  6. Neural Drive, a SuperTuxKart World Model that runs in the browser (huggingface.co)
    2 points 0
  7. Coding agent for local models on a Mac (mlx-optiq.com)
    1 points 1
  8. Frame: Grounding LLM Vulnerability Detection with a Sound Separation-Logic Core (lambdasec.github.io)
    2 points 0
  9. Mlx-optiq: per-layer mixed-precision LLM quantization for Apple Silicon (mlx-optiq.com)
    2 points 0
  10. A 1B humanizer that matches human writing on an AI detector (mlx-optiq.com)
    3 points 0
  11. Zero-Dependency Programming (conjure.pages.dev)
    2 points 0
  12. Scaling Pedagogical Pre-Training: From Optimal Mixing to 10B Tokens (huggingface.co)
    2 points 0
  13. From HashHop to Memory-Augmented Language Models (huggingface.co)
    2 points 0
  14. The Optimal Architecture for Small Language Models (huggingface.co)
    1 points 0
  15. Enhancing LLMs with LoRA – Standardized Recipes for Capability Enhancement (huggingface.co)
    3 points 0
  16. OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution (algorithmicsuperintelligence.ai)
    53 points 9
  17. Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement (huggingface.co)
    1 points 0
  18. The 1B Token Challenge: Finding the Perfect Pre-Training Mix (huggingface.co)
    6 points 0
  19. The 1B Token Challenge: Finding the Perfect Pre-Training Mix (huggingface.co)
    3 points 0
  20. Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training (huggingface.co)
    2 points 1
  21. Internal Coherence Maximization(ICM): Label-Free Unsupervised Training Framework (github.com)
    1 points 0
  22. Unsupervised Model Improvement via Internal Coherence Maximization (huggingface.co)
    1 points 0
  23. Show HN: PTS Library – Analyze LLM reasoning through "thought anchors"

    I built PTS (Pivotal Token Search), an open-source library for mechanistic interpretability analysis of language models. The core feature is generating "thought anchors" - identifying which specific sentences in a…

    2 points 0
  24. Automated Discovery of High-Performance GPU Kernels with OpenEvolve (huggingface.co)
    4 points 0
  25. Adaptive Classifier: Dynamic Text Classification with Continuous Learning (huggingface.co)
    1 points 0