HN Explorer

s-macke

↗ HN profile [ 91.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. Show HN: Maniac Mansion Reconstructed in 3D from Its Original Screens (github.com)

    I originally started experimenting with reconstructing real world objects from images with GPT-6 Astra and Blender. One of those experiments was this chair: https://simulationcorner.net/chair/chair-evolution.gif That…

    1 points 1
  3. When Washington switched off Fable/Mython 5: What happened, hour by hour (twitter.com)
    3 points 0
  4. 366-byte C program emulator can run Linux and Doom – IOCCC29 winner (github.com)
    6 points 1
  5. IOCCC29 Awards Presentation and Source Code Reveal [video] (youtube.com)
    1 points 0
  6. Show HN: I reverse-engineered the world maps of Test Drive III (1990 DOS game) (github.com)
    215 points 32
  7. Abstruse Goose Comic Archive (github.com)
    3 points 0
  8. 2026 Agentic Coding Trends Report (resources.anthropic.com)
    1 points 0
  9. AI is just starting to change the legal profession (understandingai.org)
    4 points 2
  10. Taking Local AI Development to the Max with AMD Ryzen AI Halo (amd.com)
    3 points 0
  11. Abstruse Goose Comic Archive (github.com)
    3 points 0
  12. Show HN: Reverse engineering and porting a C64 game with AI (github.com)
    2 points 0
  13. Physics-Based Simulation Free Online Book (phys-sim-book.github.io)
    3 points 0
  14. Can diffusion models solve visual Sudoku? (github.com)
    1 points 0
  15. OpenAI Researcher Jason Wei: It's obvious that it will not be a "fast takeoff" (twitter.com)
    36 points 8
  16. Reinforcement Learning Finetunes Small Subnetworks in Large Language Models (arxiv.org)
    3 points 0
  17. The simplest, fastest repository for training/finetuning small-sized VLMs (github.com)
    2 points 0
  18. Gemini 2.5 Pro won Pokémon Blue in 106k moves (twitch.tv)
    2 points 3
  19. SWE-Smith: Scaling Data for Software Engineering Agents (arxiv.org)
    1 points 0
  20. Sam Altman: we added one million users in the last hour (twitter.com)
    4 points 0
  21. Measuring AI Ability to Complete Long Tasks (arxiv.org)
    1 points 0
  22. FrontierMath Was Funded by OpenAI (lesswrong.com)
    18 points 4
  23. Grokking at the Edge of Numerical Stability (arxiv.org)
    1 points 0
  24. LLMs struggle with perception, not reasoning, in ARC-AGI (anokas.substack.com)
    5 points 0
  25. A Llama 70B finetune that has reflection baked into it's weights (huggingface.co)
    6 points 0