HN Explorer

nkko

↗ HN profile [ 78.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Internal Agents Map (github.com)
    1 points 3
  2. A Software Factory Is No Substitute for Maturity (nibzard.com)
    2 points 2
  3. Show HN: Fenrin – fast fictional names generation from phonological rules (nibzard.github.io)
    2 points 1
  4. Public company deep research demo on Atlas SDK (github.com)
    1 points 0
  5. Atlas: Open-source deep research harness (steel.dev)
    2 points 0
  6. Atlas – open-source deep research you own (github.com)
    7 points 1
  7. Building a Deep Research Agent That Survives (steel.dev)
    2 points 0
  8. Building a Deep Research Agent That Survives Its Own Failures (steel.dev)
    2 points 0
  9. An autopsy of Claude Code's deep research (steel.dev)
    3 points 0
  10. Do Better Research with NotebookLM (blog.google)
    2 points 0
  11. Errors are the last interface agents read (steel.dev)
    2 points 0
  12. Coding agent can read your .env file (bitwarden.com)
    2 points 0
  13. Agent Traces: every browser session as a prompt (steel.dev)
    2 points 0
  14. Agent-Native Extensibility (nibzard.com)
    2 points 0
  15. Trained Qwen to Write Clojure Better Than GPT-5.4 (Kinda) (nibzard.com)
    2 points 0
  16. Durable Researcher (github.com)
    1 points 0
  17. The Hard Problems Nobody Has Solved (nibzard.com)
    2 points 0
  18. Absurd: Simplest durable execution workflow system (github.com)
    3 points 0
  19. Give Claude Code a real browser (steel.dev)
    2 points 0
  20. Startup Is Probably Dead on Arrival (steveblank.com)
    3 points 0
  21. GitHub explains six February outages and fixes (github.blog)
    4 points 2
  22. The Post-Copyright Era of Software (nibzard.com)
    5 points 0
  23. BullshitBench v2: LLMs answering nonsense questions (github.com)
    2 points 0
  24. Turning web runs into scripts with Codex (nibzard.com)
    1 points 0
  25. Go vs. Python for AI Infrastructure: Benchmarks 2026 (dasroot.net)
    1 points 0