Live data from Hacker News

Viewing profile — systima

systima

HN member
Joined
Sat, Feb 28, 2026, 7:06 PM UTC
HN karma
348
Public activity
45 items

About systima

No profile information was provided.

Recent public activity

  1. story
    The Subagent Tax

    Based on feedback from our last post, we measured Claude Code subagent fan-outs vs. Doing the same work sequentially, We found that they used between 2 and (almost) 6 x the input t…

  2. comment
    Comment #48891098

    We are using Claude Max with OpenCode. See the post for details.

  3. comment
    Comment #48889840

    We've updated the post now!

  4. comment
    Comment #48889809

    UPDATE – 13/07/26: 1) We have added a repository reproducing the methods. 2) We have commented on output quality in the post (in addition to tokens/cost). 3) Per a previous update,…

  5. comment
    Comment #48883969

    UPDATE: After reading PUSH_AX's valid comment: ``` This is like saying contractor (A) asked for $33,000 to undertake the work and contractor (B) asked for $7,000 Are we measuring a…

  6. comment
    Comment #48883735

    Anecdotally, the results from OpenCode + Claude appear to be the same if not better for our uses over the past year.

  7. comment
    Comment #48883681

    We have never read your blog or your content before. Suspect that many have covered the "Comparing agentic coding tools" angle before, and that the differentiator is depth of analy…

  8. comment
    Comment #48883598

    We are yet to try Pi!

  9. comment
    Comment #48883581

    Model: Cost, mainly. The runs went through a Claude Max subscription rather than metered API billing, and pinning an older stable snapshot kept run-to-run comparisons clean and che…

  10. story
    Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

    This started based off of a hunch. We usually use OpenCode, but were 'forced' to use Claude Code for a while due to issues with Meridian. In that time, we saw the usage meter rise …

  11. story
  12. story
  13. story
    Show HN: AI skills for program / project / delivery managers

    A Claude Code and OpenCode skill library that covers the full project and engagement lifecycle through 10 stage-aligned agents and 62 workflows: * Shaping: MEDDIC qualification, RO…

  14. comment
    Comment #48271013

    Is this allowed under Apple's ToS? I recall the Beeper Mini debacle not so long ago, and fear that this may be a house built on sand.

  15. comment
    Comment #47988961

    How does this differ to Mastra?

  16. comment
  17. comment
  18. comment
    Comment #47598826

    As the entire planet now knows, the Claude Code source leaked on March 31. The engineering-focused findings have been covered extensively (fake tool injection, Undercover Mode, KAI…

  19. story
  20. comment
    Comment #47561208

    How does this differ to Open Code Desktop?

  21. comment
    Comment #47465484

    Sorry, I missed part of your question: What caused the switch was that we're building AI solutions for sometimes price-conscious customers, so I was already familiar with the patte…

  22. comment
    Comment #47464338

    Yes I regularly plan in Opus 4.6 and execute in “lesser” models ie MiniMax

  23. comment
    Comment #47462016

    Open Code has been the backbone of our entire operation (we used Claude Code before it, and Cursor before that). Hugely grateful for what they do.

  24. comment
    Comment #47436190

    I agree. In my experience, this correlates more with soft skills and “one man band” founder/maker companies that tend to sell training products or (if they do exist in a company en…

  25. comment
    Comment #47419268

    Thank you — Excellent points. Will think about them.