HN Explorer

mohsen1

↗ HN profile [ 194 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: A free and open source session recording Chrome extension

    Hey HN, This is a Chrome extension that records lots of details in a usage session. Stuff like network calls, console logs, screenshots and also optionally screenshots and user narration Tools like this exist, but every…

    1 points 0
  2. Show HN: Git-lazy-mount mount a repo without cloning it. Works with ordinary Git (github.com)

    Hello! This is an attempt to make google3 style repo clones work with Git. In a HN thread a few days ago the idea sparked for me. It can be super useful for very large repos that need to be cloned for AI coding sessions…

    9 points 2
  3. AI is killing All About Berlin (twitter.com)
    7 points 1
  4. Sound Mode: Can TypeScript Type Checking Be Stricter? (tsz.dev)
    6 points 5
  5. Bypass internet blockade in Iran via Vercel (github.com)
    6 points 0
  6. Image Generators Are Generalist Vision Learners (arxiv.org)
    2 points 0
  7. SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Task (arxiv.org)
    1 points 0
  8. Ceno, browse the web without internet access (ceno.app)
    134 points 20
  9. Show HN: A compression tool that reduces linux binary downloads by 6%

    I wanted to see if AI (mostly ChatGPT Pro and Gemini Pro 3.1) could figure out how to compress executable binaries better than existing generic tools without me actually knowing much about compression engineering or ELF…

    3 points 1
  10. Show HN: I used LLMs to build a compression tool that beats xz on x86_64 ELFs

    I wanted to see if AI (mostly ChatGPT Pro and Gemini Pro 3.1) could figure out how to compress executable binaries better than existing generic tools without me actually knowing much about compression engineering or ELF…

    4 points 3
  11. Tons of Free Potato in Berlin (4000-tonnen.de)
    4 points 1
  12. Mafia Arena: Benchmarking LLMs in the game of mafia (mafia-arena.com)
    3 points 0
  13. Show HN: Mafia Arena – LLMs play social deduction games against each other (mafia-arena.com)

    Hello! Over the Christmas break I built a platform where LLMs play the party game Mafia against each other. 11 AI players, full conversations, voting, deception — the whole thing. Why? Benchmarks like MMLU test…

    1 points 0
  14. ElevenLabs Music (elevenlabs.io)
    5 points 0
  15. Scribe (elevenlabs.io)
    4 points 1
  16. Show HN: Letting LLMs Run a Debugger (github.com)

    Hey HN, I just built an experimental VSCode extension called LLM Debugger. It’s a proof-of-concept that lets a large language model take charge of debugging. Instead of only looking at the static code, the LLM also gets…

    147 points 31
  17. Train your own R1 reasoning model with Unsloth (unsloth.ai)
    6 points 0
  18. Ask HN: Is anyone working on an LSP-based AI debugger?

    It seems that most solutions focus on providing an LLM with the code (and sometimes the test failures) and then asking it to produce a new version that might work. I’ve had great success with this method already and…

    1 points 0
  19. Askds – Ask DeepSeek R1 to debug your tests (github.com)
    2 points 1
  20. Yek: Serialize your code repo (or part of it) to feed into any LLM (github.com)
    205 points 77
  21. Show HN: stop-nagging A CLI tool to silence upgrade nags and telemetry in tools

    Stop-nagging is a Rust CLI tool I built to automatically silence those annoying upgrade prompts, telemetry, and advertising nags that plague our development tools. It works by setting environment variables and running…

    6 points 0
  22. Help me add dark mode in Hacker News natively (github.com)
    25 points 22
  23. Learning to Drive by Imitating the Best and Synthesizing the Worst (arxiv.org)
    7 points 1
  24. Applying Deep Learning to Airbnb Search (medium.com)
    6 points 0
  25. OpenOffice can't print on Tuesdays (bugs.launchpad.net)
    3 points 0