HN Explorer

josefchen

↗ HN profile [ 88.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. OpenAI puts Pro subscriptions on hold due to Astra demand (techcrunch.com)
    1 points 0
  2. ChatGPT puts 20x Plan on hold (help.openai.com)
    1 points 2
  3. Flavourbench: LLM Eval with Executable Culinary Ground Truth (arxiv.org)
    1 points 0
  4. Anthropic launches Fable 5.1 and Mythos 5.1 (bloomberg.com)
    1 points 1
  5. Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control (arxiv.org)
    1 points 0
  6. AI Inference chips will end the same as Crypto Mining ASICs (twitter.com)
    1 points 0
  7. The AI Data-Centre Bust Will Look Like a Boom (josef.cn)
    2 points 3
  8. Turks All the Way Down (josef.cn)
    3 points 0
  9. Co-Failure Ceiling on Mixture-of-Agents Across 67 Frontier Models (huggingface.co)
    2 points 0
  10. Testing 67 Models: Combining LLMs Rarely Beats the Best Single Model (huggingface.co)
    2 points 0
  11. Combining LLMs Rarely Beats the Best Single Model, I tested 67 frontier models (arxiv.org)
    1 points 0
  12. A 10-KB model that decides when a 4B-parameter robot policy wakes up (huggingface.co)
    2 points 0
  13. Aegis: A Backup Reflex for Physical AI (arxiv.org)
    2 points 0
  14. Foxconn and TSMC are running an 800-year-old operating system (twitter.com)
    4 points 0
  15. Aura: Action-Gated Memory for Robot Policies at Constant VRAM (huggingface.co)
    3 points 0
  16. 3 points 0
  17. Aura: Action-Gated Memory for Robot Policies at Constant VRAM (arxiv.org)
    3 points 0
  18. 1 points 0
  19. 1 points 0
  20. 1 points 0
  21. 1 points 0
  22. First culinary feature extraction models (huggingface.co)
    2 points 0
  23. All of human cooking compressed into 2 megabytes (arxiv.org)
    444 points 55
  24. LLMs understand flavours without ever tasting anything (arxiv.org)
    3 points 0
  25. 1 points 0