Live data from Hacker News

Viewing profile — rubenflamshep

rubenflamshep

HN member
Joined
Mon, Jan 05, 2026, 5:51 PM UTC
HN karma
54
Public activity
56 items

About rubenflamshep

I write about LLMs and Agentic AI - rubenflamshepherd.com

Recent public activity

  1. comment
    Comment #49211275

    I also tried Herdr. But I'm already using Aerospace, which makes MacOS window management a breeze and I don't need the remote session management stuff so the benefit wasn't quite t…

  2. comment
    Comment #49211127

    My workflow has become a sort of "living process". When I encounter friction in some part of it, I focus my attention on it, it adapts, grows from from an annoyance to something th…

  3. comment
    Comment #49051180

    It's like that all that knowledge exists as a vague memory. I've found if I ask them specifics about any book I've read (w/o allowing tool calling), when they get it wrong their ha…

  4. comment
    Comment #49050550

    The issue remains the context window. I haven't seem any example of a "memories" system that the agent can update over time without it devolving into slop. The magic of the human b…

  5. comment
    Comment #49050523

    Looks cool! I think we're all vibe-coding our own menu bar usage apps :)

  6. story
    Show HN: I built a blind taste test for Claude and Codex designs

    Hey HN! A while back I asked Codex to generate a companion site for a book I was enjoying. It ended up generating a landing page for the book that was ...actually good? I went down…

  7. comment
    Comment #48853556

    When I was going through this it was because OpenAI had defaulted to /fast mode with 2x token usage

  8. story
  9. comment
    Comment #48210744

    Nah, if a human can't be bothered to write it themselves, I can't be bothered to read it.

  10. comment
    Comment #48051053

    Hmmm, I disagree. The AI is exceedingly average at everything it does and requires an expert human-in-the-loop to catch things that appear plausible but are slop. To that degree I …

  11. comment
    Comment #48051030

    Some engineers I work with have had less than desirable results with /simplify but it overall seems to work! I used to use some of the humanlayer subagents but they haven't been up…

  12. comment
    Comment #48024578

    I find all of these .md files released by the labs to be ai generated slop. The only exception being maybe the /simplify command

  13. story
  14. comment
    Comment #47601702

    This loads some bars and then just breaks for me :(

  15. comment
  16. story
    Show HN: Agentic Data Analysis with Claude Code

    Hey HN, as a former data analyst, I’ve been tooling around trying to get agents to do my old job. The result is this system that gets you maybe 80% of the way there. I think this i…

  17. comment
    Comment #47325668

    Very cool! One small UI grip: When I play a song the control at appears in the bottom of the page blocks the footer on the main page. I assume you looked into automating the charts…

  18. comment
    Comment #47198353

    There is no chart or table in the original paper. Feels like the one in the LLM-generated page is probably hallucinated?

  19. comment
    Comment #47156046

    I've found VSCode _ok_ to work with across across different workspaces/projects. The window memory is hit and miss. There's a secondary side bar I've been trying to NOT have open o…

  20. comment
    Comment #47107065

    People are getting caught up in the "fast (but slow) diffusion)" that Dario has spoken to. Adoption of these tools has been fast but not instant but people will poke holes via "wel…

  21. comment
    Comment #47049115

    Interesting. What would you say is your ratio of "sit down and make the implementation" time to "multi-agent system builds the thing" time?

  22. comment
    Comment #47048849

    Same. The only situation when I've consistently gotten a system to run for 20+ minutes was a data-analysis with tight guardrails and explicit multi-phase operations. Outside that I…

  23. comment
    Comment #47035723

    Quick plus one for Capital One after also working there. They're by far the most tech-forward of all the larger financial institutions, and by virtue of being a FI they take data-s…

  24. comment
    Comment #46990866

    I'm on desktop!

  25. comment
    Comment #46990856

    I think the key here is having the network with the high-roller clients. The ability to execute is down funnel of that.