HN Explorer

Jet_Xu

↗ HN profile [ 75.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. Strong feeling: we are in a folded AI reality

    Some people think Agentic AI could do everything, is getting more and more powerful even feel fear about it. Another group non-technical people still just trapped in the LLM chat is weak and full of hallucination world.…

    1 points 1
  4. 1 points 0
  5. 1 points 0
  6. Show HN: DocMason – Agent Knowledge Base for local complex office files (github.com)

    I think everyone has already read Karpathy's Post about LLM Knowledge Bases. Actually for recent weeks I am already working on agent-native knowledge base for complex research (DocMason). And it is purely running in…

    11 points 2
  7. 1 points 0
  8. Ask HN: Whether there is LLM or other strong NLP behind Hacker News?

    I found that if your post is a LLM generated content, it will be auto-hide. And I heard long time ago for same product you could not share in Show HN for multiple times. What is the mechanism behind? Is Hacker News…

    3 points 2
  9. Ask HN: The repo is the app. Codex is the runtime. Could this be future pattern?

    I am developing a repo-native agent app for analyst-grade answers over complex private file. The initial idea is: I want codex could help me to deep dive digest all my work files (tons of ppt, excel & doc), and then…

    1 points 0
  10. 1 points 0
  11. Are you drowning in AI code review noise? 70% of AI PR comments are useless

    Most AI code review tools generate 10-20 comments per PR. The problem? 80% are noise. Here's a framework for measuring signal-to-noise ratio in code reviews - and why it matters more than you think.…

    2 points 0
  12. 1 points 0
  13. 1 points 1
  14. Show HN: AI code reviewer that analyzes cross-module impacts

    Hey HN! I'm Jet, building LlamaPReview. Most AI code reviewers only see the diff. They miss the real risks: a function rename that breaks 5 other files, a dependency change that shifts your architecture, a "small" PR…

    1 points 0
  15. 1 points 0
  16. 1 points 0
  17. 1 points 0
  18. Ask HN: DeepSeek V3's AI Code Review Performance – A Reality Check with Data

    I recently conducted a detailed benchmark of various LLMs for AI code review, specifically focusing on Pull Request analysis. The results were quite surprising and contradict some recent marketing claims. Test setup:…

    2 points 1
  19. Ask HN: AWS DynamoDB Triggers – A Time Bomb in Your Production Environment?

    I recently discovered what I consider a serious design flaw in AWS DynamoDB Triggers that I believe deserves more attention from the community. Here's the issue: DynamoDB Triggers can only point to the `$LATEST` version…

    3 points 3
  20. What do you check first in PR review? Help shape our AI Code review tool (github.com)
    1 points 1
  21. Lessons Learned: Migrating to Mistral-Large-2411 for Production Code Reviews (medium.com)
    4 points 1
  22. Show HN: LlamaPReview – AI code reviewer trusted by 2000 repos, 40%+ effective (jetxu-llm.github.io)

    Hi HN! A month ago, I shared LlamaPReview in Show HN[1]. Since then, we've grown to 2000+ repos (60%+ public) with 16k+ combined stars. More importantly, we've made significant improvements in both efficiency and review…

    2 points 0
  23. Ask HN: Are We Approaching Code Reviews Wrong?

    As a tech lead, I recently tracked my team's time and found we spent an average of 12.5 hours per developer per week on PR reviews(include discussion of PR review results) - more than half of our coding time! This led…

    2 points 0
  24. Show HN: LlamaPReview – AI GitHub PR reviewer that learns your codebase (github.com)

    I built LlamaPReview to solve a common frustration: most AI code reviewers either require complex setup or don't truly understand project context. Key differentiators: 1. One-click installation through GitHub…

    85 points 45
  25. Show HN: Llama-GitHub – LLM-Powered GitHub Context Retrieval Python Library (github.com)

    Hi HN, I’m excited to share llama-github, an open-source Python library. Llama-github is a powerful tool that helps you retrieve the most relevant code snippets, issues, and repository information from GitHub based on…

    3 points 1