HN Explorer

wek

↗ HN profile [ 167 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering (arxiv.org)
    2 points 0
  2. Configuring Agentic AI Coding Tools: An Exploratory Study (arxiv.org)
    3 points 0
  3. Building the harness around our coding agents. Eight failure modes and pillars (nimbalyst.com)
    3 points 0
  4. Constraint Decay: The Fragility of LLM Agents in Back End Code Generation (arxiv.org)
    287 points 55
  5. Show HN: Nimbalyst open source Obsidian, Codex app, and Linear for coding agents (github.com)

    Hi, I'm Karl. Greg and I spent the last year building Nimbalyst, an open-source local desktop workspace for working with coding agents. We want to give agents and humans one place to work together with maximum bandwidth…

    7 points 1
  6. 1 points 0
  7. Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering (arxiv.org)
    2 points 0
  8. The Code Agent Orchestra: what makes multi-agent coding work (addyosmani.com)
    2 points 1
  9. Managing context in long-run agentic applications (slack.engineering)
    2 points 0
  10. Jetbrain's Research: Understanding AI's Impact on Developer Workflows (blog.jetbrains.com)
    1 points 0
  11. 1 points 0
  12. Speed at the cost of quality: Study of use of Cursor AI in open source projects (2025) (arxiv.org)
    148 points 27
  13. Ask HN: How is your team collaborating while working with coding agents?

    I'm curious how your team is working with Claude Code and Codex and collaborating? Are you working with Linear and JIRA and just MCPing. Are your moving things from your markdown to a Google Doc or Notion to collaborate…

    3 points 4
  14. AI is an enchantment, not a level booster

    It is a multiplier on the stats you already have

    2 points 0
  15. One plan/spec to rule them all (at least replace lots of docs)

    There have been lots of talk about PRDs being dead and spec-driven development etc. Here is how we are planning. We iterate with our team and agents on one plan document. It starts with some of the key things in a PRD…

    3 points 0
  16. Workflow to build context for coding agents

    Here’s the workflow my team and I have found works best with coding agents: - Plan: Write a plan in markdown. Edit this. Iterate. The plan isn’t a throwaway note. It tracks status as work progresses (draft ->…

    3 points 1
  17. Things I keep reminding myself about while working with AI Agents

    I am a founder working 12 hours a day with Claude Code and Codex. I think that AI is on the order of at least the industrial revolution, if not the agricultural revolution in terms of how it will remake things. I make…

    2 points 1
  18. Comprehensive Benchmarking of Agentic Systems Across 104 Real-World Challenges (arxiv.org)
    1 points 0
  19. 1 points 0
  20. Local WYSIWYG Markdown, mockup, data model editor powered by Claude Code (nimbalyst.com)

    We have been getting the best results with Claude Code when we iterate with it to build full context and then use and update that context as we work. So, we built Nimbalyst to be the local WYSIWYG editor and session…

    29 points 3
  21. 1 points 0
  22. The AI-Native Software Development Lifecycle: Theoretical/ Practical Methodology (arxiv.org)
    1 points 1
  23. 1 points 0
  24. 3 points 1
  25. 1 points 0