HN Explorer

diwank

↗ HN profile [ 261 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. A gas-enshrouded and gas-reddened black hole at cosmic dawn (nature.com)
    4 points 0
  2. Ask HN: Which is the least sloppy and claudeism free model you have used?

    I feel like recent models have been consistently getting more sloppy and increasingly claude-ism heavy (load-bearing seams galore) with every new release. I was hoping this trend would reverse in newer major version…

    4 points 0
  3. Anthropic releases Claude Fable 5 (theverge.com)
    4 points 0
  4. Sonny Rollins Is Dead (nytimes.com)
    1 points 0
  5. Breakthrough Prize Announces 2026 Laureates (breakthroughprize.org)
    3 points 0
  6. Reasoning models encode tool choices before they start reasoning (arxiv.org)
    3 points 0
  7. Show HN: Datetime-bench: which datetime formats LLMs get right (and wrong) (github.com)

    tl;dr * If you need an LLM to parse OR emit a timestamp, use: RFC 3339 ( e.g. 2024-03-26 10:30:00-05:00 ) * python date format also works well * Do NOT use unix epoch or javascript date formats. * Smaller models and…

    2 points 1
  8. Show HN: Dropbox for Your Agents' Memories (memory.store)
    2 points 0
  9. Show HN: IQT – Why space feels panoramic and time feels fleeting (github.com)

    I've spent the past year building a theory of phenomenal experience (consciousness) that's designed to be falsifiable. It identifies phenomenal quality with a specific mathematical object (the algebra-state pair on a…

    1 points 0
  10. Putting Gemini to Work in Chrome (blog.google)
    56 points 20
  11. From kinetic gases to an exponentially expanding universe (iopscience.iop.org)
    1 points 0
  12. DeepSeek-v3.2 and v3.2 Speciale Announced (huggingface.co)
    5 points 0
  13. Effective harnesses for long-running agents (anthropic.com)
    125 points 12
  14. Cursor 2.0 – A step in the wrong direction (forum.cursor.com)
    3 points 1
  15. Stress-testing model specs reveals character differences among language models (alignment.anthropic.com)
    2 points 1
  16. Thinking Sparks: Emergent Attention Heads in Reasoning Models (arxiv.org)
    1 points 0
  17. The contextvars and the chain of asyncio tasks in Python (valarmorghulis.io)
    2 points 0
  18. AI Village: Watch frontier AIs interact with each other and the world (theaidigest.org)
    3 points 0
  19. Discovery of Unstable Singularities in Navier Stokes (DeepMind) (arxiv.org)
    2 points 0
  20. Llama.cpp: Deterministic Inference Mode (CUDA): RMSNorm, MatMul, Attention (github.com)
    6 points 0
  21. New Ways to Use NotebookLM (blog.google)
    4 points 0
  22. Veo 3 and Veo 3 Fast – new pricing, new configurations and better resolution (developers.googleblog.com)
    2 points 0
  23. Using AI to perceive the universe in greater depth (deepmind.google)
    55 points 23
  24. The Himalayan village where you can see the cosmos (bbc.com)
    3 points 0
  25. Beyond the terminal: Gemini CLI comes to Zed (developers.googleblog.com)
    3 points 0