Live data from Hacker News

Viewing profile — stpedgwdgfhgdd

stpedgwdgfhgdd

HN member
Joined
Mon, May 29, 2017, 5:29 PM UTC
HN karma
146
Public activity
150 items

About stpedgwdgfhgdd

14bijenwas.kweeperen@icloud.com

Recent public activity

  1. comment
    Comment #49179308

    Interesting that a date format is used for MCP-Protocol-Version.

  2. comment
  3. comment
    Comment #49003392

    These routers can be interesting on a company level to optimize for cost and quality, but for individuals who mostly work on the same tasks, i doubt it. You want to leverage the ca…

  4. comment
    Comment #48976082

    My son setup a minecraft server on a mac mini using claude, was pretty smooth. If your kids just use it in house you do no need to worry about security issues. In my case I did cre…

  5. comment
    Comment #48855983

    Lots of unit test do not add value in the traditional sense, but they do help the llm to understand the code.

  6. comment
    Comment #48855962

    Same for me, that is why I switched to Pi. I still use Sonnet or Opus, but mainly GPT due to cost.

  7. comment
    Comment #48848338

    Pi is meant for people who know what they are doing. If you dont fall into that category use OpenCode, etc. The whole idea is that you customize Pi to your own needs by asking it t…

  8. comment
    Comment #48742803

    +1 the distinction between personal projects and Enterprise development is a big one. A severe bug in my personal projects, i fix it on the fly. A bug in our products rolled out, n…

  9. comment
    Comment #48690503

    404, typescript deployment?

  10. comment
    Comment #48689053

    The thing I do not get with these routers is that you will have more cache misses (5min ttl). And if there is one thing i’ve learned; using the cache is crucial. How does this rout…

  11. comment
    Comment #48595210

    Built my own using Claude Code; inside a gitlab job we call Claude Code headless. This works well. There is a tiny mcp server exposed to Claude so it can post inline comments. All …

  12. comment
    Comment #48591415

    “People dramatically underestimate what thousands of organized humans can accomplish when they are adequately fed, aggressively supervised, and denied alternative career paths.“

  13. comment
    Comment #48232858

    For those who also get fed up by the ever growing (unstable) coding agents, check out Pi. It is not for everyone but for the diehards it is good.

  14. comment
    Comment #48232820

    I just dont get why people choose Python and not e.g. Go for high performance problems.

  15. comment
    Comment #48064694

    I m running into similar issues, more and more i’m removing complexity from the agent to the (Go) logic in order to make it more deterministic. To be more precise; everything is pr…

  16. comment
    Comment #47707072

    “We collect the native tool calls and bash commands” Holy shit, I cant imagine this to hold for every bash command Claude Code executes. That would be terrible, probably violating …

  17. comment
    Comment #47451499

    You can ask it to /simplify Related, it seems to me that there are two types of tests, the ones created in a TDD style and can be modified and the ones that come from acceptance cr…

  18. comment
    Comment #47375478

    Start over, create a new plan with the lessons learned. You need to converge on the requirements.

  19. comment
    Comment #47356750

    Try the latest skill-creator, has a/b testing

  20. comment
    Comment #47355884

    “ MCP support. Axe can connect any MCP server to your agents” I just don't see this in the readme… It is not in the Features section at least. Anyway, i have MCP server that can po…

  21. comment
    Comment #47285738

    No worries. True, you need to learn new skills to work properly with Claude. However, 30 yrs of coding experience come in handy to quickly detect it is going in the wrong direction…

  22. comment
    Comment #47247471

    I don’t think this an AI specific problem, same can happen with humans.

  23. comment
    Comment #47087037

    I build a code reviewer based on the claude code sdk that integrates with gitlab, pretty straightforward. The hard work is in the integration, not the review itself. That is taken …

  24. comment
    Comment #47086978

    OR - OR? And - And Exoskeleton AND autonomous agent, where the shift is moving to autonomous gradually.

  25. comment
    Comment #46903900

    Exactly, one out of four or three prompts require tuning, nudging or just stopping it. However it takes seniority to see where it goes astray. I suspect that lots of folks dont eve…