Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: WoseApp – a social network where every reply is a private conversation(woseapp.com ↗)
    discuss
  2. The wonder of human made art(danieldeboulay.com ↗)
    discuss
  3. Liquid Glass adoptions over and100 apps(liquidglassradar.com ↗)
    discuss
  4. Make an educated guess on Fermi-style trivia questions(playdaily.org ↗)
    discuss
  5. Jemalloc 5.4.0(github.com/jemalloc ↗)
    discuss
  6. Nowmine(nowmine.site ↗)
    discuss
  7. Ask HN: Why have we normalized jobs and soft skills bullshit so much?
    discuss
  8. The Scourge of x86 Emulation(fex-emu.com ↗)
    discuss
  9. Ngrx Inspector(visualstudio.com ↗)
    discuss
  10. Reflections on Trusting Trust, Revisited: Poisoning Self-Modifying AI Coding(arxiv.org ↗)
    discuss
  11. Hacker
    2comments
  12. Anderon (IBM) finalizes $1B CHIPS award for US quantum foundry R&D(ibm.com ↗)
    discuss
  13. A Bitter Lesson for Data Filtering(arxiv.org ↗)
    1comments
  14. Mojo 1.1: the compiler now accepts contributions(modular.com ↗)
    discuss
  15. Show HN: Continuity – project state your AI sessions can't silently contradict(github.com/vikcena01 ↗)
    discuss
  16. Show HN: Free Tournament Bracket Maker and Generator(snapbracket.com ↗)
    discuss
  17. macOS 27 is a lifesaver for killing leftover AI Agent processes(9to5mac.com ↗)
    2comments
  18. The Provenance Tax: How LLM Watermarking Changes AI Agent Behavior(lasso.security ↗)
    discuss
  19. Waymo in Singapore(waymo.com ↗)
    1comments
  20. The Concerns Surrounding Rapid Rise of AI and What We Should Do About It(medium.com/f9121212 ↗)
    discuss
  21. Age of Beyond [video](youtube.com ↗)
    discuss
  22. Natural General Intelligence(naturalgeneralintelligence.ai ↗)
    discuss
  23. Youper is shutting down – What kills mental health AI?(youper.ai ↗)
    discuss
  24. Show HN: Free GitHub Action that scans PR diffs for malicious code, not quality(github.com/marketplace ↗)
    discuss
  25. The Bitterest Lesson(typesafe.ai ↗)
    discuss
  26. Google announces new experimental "CC" AI agent for families(arstechnica.com ↗)
    discuss
  27. Show HN: Green Screen Remover – free in-browser chroma key, nothing uploaded(greenscreenremover.net ↗)
    discuss
  28. I built the fastest PHP webserver in the world(qbixserver.com ↗)
    discuss
  29. Data
    discuss
  30. Running OpenBAO on Kubernetes with a CloudNativePG PostgreSQL Back End(cncf.io ↗)
    discuss

Lodestar – Easier Communication with Agents

2 pointsby 1h agotry-lodestar.com
1 comments
1h agoHN ↗

As I leverage coding agents to tackle more complex tasks, I wanted better tools for a few specific things that I spend a lot of my energy on:

- Reading long agent proposals - Aligning agent's mental model with mine - Keeping several fronts of explorations and making sure they stay coherent - Resolving tensions across tasks or branches of ideas - Cross-pollinate good ideas across tasks

And Lodestar is an attempt to reduce the cognitive burden for those efforts.

Features:

- Inline graphs and annotations for complex ideas from agents

- Focused "read mode" for messages and docs

- Inline comments on messages, graphs, docs, html previews

- Semantic search across sessions & docs for quick retrieval

- Graph presentation of topic relationship across sessions

- Cross-session and cross-harness messaging for agent coordination

- Quick access to recent screenshots when writing a message

- Drag and drop sessions for quick reference when writing a message

And more.

Please give it a try. Let me know if you like it or hate it.