HN Explorer

opwizardx

↗ HN profile [ 92.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. I made vector search the default. My agents did better with BM25 (kolesnik.io)
    1 points 0
  2. Ask HN: Why still no unified standard file to describe all skills/mcps for repo?
    1 points 2
  3. If you can't fix the models you use, fix your workflows (kolesnik.io)
    1 points 0
  4. Show HN: Pond – lossless archive for agent sessions in your own S3 (github.com)

    I wanted all of my sessions preserved in one S3 storage dump I could access from anywhere. I couldn't find anything that could store sessions from multiple machines in one remote S3 bucket without running a database…

    1 points 1
  5. Toggles Considered Harmful (ignorethecode.net)
    15 points 8
  6. Claude Code context management: when to /clear and when to /compact (tim-schipper.nl)
    2 points 1
  7. Half the tokens for the same 36 tool calls: optimizing a coding agent (app.nz)
    2 points 0
  8. Uber open-sourced its security monitoring for Claude Code, Cursor and Codex (github.com)
    3 points 0
  9. TencentDB Agent Memory: A team-level memory hub for AI agents (github.com)
    2 points 0
  10. Better tools made Copilot code review worse. Here's how we actually improved it (github.blog)
    3 points 0
  11. How we set up our cloud agent environment (cursor.com)
    1 points 0
  12. Six Agent Harness Capabilities for Higher Model Performance (developer.nvidia.com)
    2 points 0
  13. Claude-video – Give Claude the ability to watch any video (github.com)
    1 points 0
  14. Hallmark – Anti-AI-Slop Design Skill for Claude Code, Cursor, and Codex (github.com)
    7 points 6
  15. The new rules of context engineering for Claude 5 generation models (claude.com)
    14 points 1
  16. NInfer: 271 tok/s (543 with speculative) for Qwen3.6-35B-A3B on one RTX 5090 (github.com)
    2 points 1
  17. We probed a pinned GPT-5.5 endpoint: every request carried ~1,447 hidden tokens (tosea.ai)
    4 points 1
  18. Don't Put an LLM Behind an MCP Server (spletzer.com)
    2 points 0
  19. ArcBox: From-Scratch Container Runtime for macOS in Rust (Docker, K8s, MicroVMs) (github.com)
    3 points 0
  20. Retok: Token-efficiency analyzer for Claude Code and Codex CLI (zero deps) (github.com)
    2 points 0
  21. Claude Code's system prompts, extracted and tracked across 237 versions (github.com)
    2 points 0
  22. Lobotomized Claude Code: system-prompt overrides for Opus 4.7 (github.com)
    2 points 0
  23. Ask HN: Claude Sonnet 4 API returning model with April 2024 knowledge cutoff

    Testing the claude-sonnet-4-20250514 endpoint, I'm getting a model that identifies as Claude 3.5 Sonnet with April 2024 knowledge cutoff. It doesn't know about 2024 election results or events after April 2024.…

    1 points 1