Top all-time · #9795
minusx.ai
Company blog · minusx.ai/blogaiprogramming
minusx.ai is the company blog at minusx.ai, writing about ai and programming. Since 2024, 7 different Hacker News readers have linked it 11 times, most often “What makes Claude Code so damn good”. It is still writing: the last post was on 2025-08-21, and you can follow it by feed.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
Linked for a post decoding Claude Code's internals, including its plan mode and exit-plan-mode tool, and for a privacy policy page. One commenter called the Claude Code post informative.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Organize your company's data and put agents to work.
Most-linked posts?
- What makes Claude Code so damn good5 people · 6 mentions · first linked 2025-08-21
What Hacker News says?
I thought this was informative: https://minusx.ai/blog/decoding-claude-code/
Comment linking /blog/decoding-claude-code/
on “You should write an agent”Submitted What makes Claude Code so damn good as a story · 469 points
HN discussionIt does not write anything in plan mode, it's documented here it has only readonly tools available in plan mode: https://docs.anthropic.com/en/docs/claude-code/common-workfl... But here are fine prints, it has "exit plan mode" tool, documented here: https://minusx.ai/blog/decoding-claude-code/#appendix So it can exit plan mode on its own and you wouldn't know!
Comment linking /blog/decoding-claude-code/
on “A staff engineer's journey with Claude Code”Submitted Decoding Claude Code as a story · 4 points
HN discussionThis very narrow very specific single-purpose task-oriented subagent was one of the first things talked about in this every lovely recent & popular submission (along with other fun to read points): What makes Claude Code so damn good (and how to recreate that magic in your agent)!? https://minusx.ai/blog/decoding-claude-code/ https://news.ycombinator.com/item?id=44998295
Comment linking /blog/decoding-claude-code/
on “Don't Build Multi-Agents”Submitted What Claude Code Does Differently: Inside Its Internals as a story · 3 points
HN discussionWe're currently exploring the tools displayed on our website (Tableau, Grafana, Colab, & Google Sheets). But if you have a specific tool in mind, please do tell us at https://minusx.ai/tool-request
Comment linking /tool-request
on “Launch HN: MinusX (YC S24) – AI assistant for data tools like Jupyter/Metabase”Submitted LLM output tokens are upto 200x slower than input tokens as a story · 3 points
HN discussionI totally share your concerns about data (especially data that may be sensitive). We have a simple non-legal-speak privacy policy here: https://minusx.ai/privacy-simplified . > Are your LLMs running entirely locally on your own hardware, and if not, how can you say the data is not shared with third parties? (EDIT: you mentioned GPT-4o in another comment so this statement cannot be correct.) We're currently only usin…
Comment linking /privacy-simplified
on “Launch HN: MinusX (YC S24) – AI assistant for data tools like Jupyter/Metabase”Submitted Motivations on building a FOSS browser extension as a story · 3 points
HN discussionSubmitted What Claude Code gets right as a story · 2 points
HN discussion