HN Explorer

anima-core

↗ HN profile [ 64.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. All of you doubted me, and said I was hallucinating on AI (ryanshamim.substack.com)
    1 points 1
  2. 1 points 0
  3. 1 points 0
  4. 1 points 0
  5. We keep making transformers faster. What if we don't need them at all? (zenodo.org)
    1 points 1
  6. A One-Shot Catastrophe Avoidance Benchmark for RL Agents (zenodo.org)
    2 points 1
  7. Semantic Field Execution: Decoupling Transformers from Runtime Inference (zenodo.org)
    1 points 1
  8. The Inference Efficiency Paradox (substack.com)
    2 points 0
  9. Post-transformer inference: 224× compression of Llama-70B with improved accuracy (zenodo.org)
    72 points 13