HN Explorer

grbsh

↗ HN profile [ 240 ms ] full profile

No user record in our sample, but grbsh has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. I Hate My Friend (wired.com)
    3 points 0
  2. Show HN: Knowledgework – AI Extensions of Your Coworkers (knowledgework.ai)

    Hey HN! We’re building Knowledgework.ai, which creates AI clones of your coworkers that actually know what they know. It's like having a version of each teammate that never sleeps, never judges you for asking "dumb"…

    8 points 2
  3. Nat Friedman – Some things I believe (nat.org)
    5 points 0
  4. Show HN: Baml_vcr -Record your LLM calls and play them back during tests (github.com)
    2 points 0
  5. Show HN: Screenshock.me – Zap yourself into being productive with browser AI (screenshock.me)

    I recently got the Pavlok, a wrist worn device that is capable of delivering a shock (intended for negative reinforcement of behaviors). But, you have to manually trigger it yourself. So, I decided to continuously…

    3 points 1
  6. 1 points 0
  7. Knowledgework: a digital second brain for your work (knowledgework.ai)
    3 points 1
  8. Show HN: BlinkAlarm - Prevent eyestrain, dryness with real-time computer vision! (github.com)

    I often struggle with dry, strained eyes from long duration computer usage. It turns out when focusing intently, human blink rates decline from a healthy 15-20 per minute to 3-4 (or even fewer in some cases). I wrote a…

    4 points 0
  9. How to inference-time compute scale your human software engineerin (speculativeinference.bearblog.dev)
    2 points 0
  10. 1 points 0
  11. Ask HN: How to improve program design / abstraction ability? Resources?

    With LLMs allowing me to write code so much faster, I'm much more quickly hitting tech debt walls (no doubt some to degree because I am using LLMs to write to code). Rather, I'm much more quickly realizing the ways in…

    2 points 1
  12. Show HN: Jsonltui – CLI to inspect large JSON files and localize parsing errors (github.com)
    4 points 0
  13. Show HN: Jsonltui – Fast TUI and webui to inspect and debug parsing JSONL (github.com)
    4 points 0
  14. LLMs are variable ambiguity, variable precision compilers (github.com)
    1 points 0
  15. Show HN: Peripheral – test and train peripheral vision in browser (github.com)
    5 points 0
  16. How to use Claude as a PRD compiler (github.com)
    1 points 0
  17. Show HN: Repogather – copy relevant files to clipboard for LLM coding workflows (github.com)

    Hey HN, I wanted to share a simple command line tool I made that has sped up and simplified my LLM assisted coding workflow. Whenever possible, I’ve been trying to use Claude as a first pass when implementing new…

    65 points 35
  18. LLM coding autopilots still need a steering wheel (and they will for a while) (grbsh.substack.com)
    1 points 0
  19. HypochondriacGPT (hypochondriac.xyz)
    3 points 0
  20. Show HN: Experimenting with generating SVG diagrams and visualizations (slidemagic.framer.ai)

    I ran a quick experiment to see if I could generate SVGs using an LLM with good layout. This is an interesting task, because it requires spatial reasoning and planning (it can easily start off well-laid out, but run out…

    1 points 0
  21. 1 points 1
  22. How to write code so that LLMs can extend it (grbsh.substack.com)
    10 points 3
  23. CoT prompts don’t help with “system 1” thinking, and other prompting principles (grbsh.substack.com)
    2 points 2
  24. Large Language Models and the End of Moore’s Law (grbsh.substack.com)
    3 points 0
  25. Show HN: Categorcle, a GPT-powered creativity / improv training daily game (categorcle.app)
    1 points 0