HN Explorer

pauliusztin

↗ HN profile [ 83.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. Took apart Claude Code, then turned it into a free course on harness engineering

    The fastest way to learn harness engineering? Build Claude Code from scratch. Why harness engineering? LangChain kept the same model and changed only the harness. Their coding agent went from 53% to 67% on…

    1 points 3
  3. 1 points 0
  4. 1 points 0
  5. 1 points 0
  6. 1 points 0
  7. 1 points 0
  8. 1 points 0
  9. 1 points 0
  10. 1 points 0
  11. 1 points 0
  12. 1 points 0
  13. I reverse-engineered the three biggest agent-memory tools

    I spent weeks reading about how Cognee, Graphiti, and Neo4j's `agent-memory` build their agent memory architectures. They converged on the same heavy knowledge-graph design: an ontology, LLM extraction pipelines,…

    2 points 4
  14. 1 points 0
  15. 3 dangers of being locked into a harness. Your context layer is true freedom

    Models are commoditizing fast. Harnesses already have. A "free" open-source harness feels like freedom, but the deeper I built in, the more I'd lose. "Free" open-source harnesses don't make you free. Staying coupled to…

    1 points 0
  16. 1 points 0
  17. 1 points 0
  18. 1 points 0
  19. I spent a year building agent memory on knowledge graphs. Here are my 5 mistakes

    I spent the past year building a unified memory layer for my AI agents using knowledge graphs and ontologies on top of MongoDB. I followed every trend first. I reached for the shiny frameworks and tried to design the…

    3 points 1
  20. 1 points 0
  21. 1 points 0
  22. 1 points 0
  23. 1 points 0
  24. 1 points 0
  25. 1 points 0