Live data from Hacker News

Viewing profile — bartek_gdn

bartek_gdn

HN member
Joined
Tue, Mar 14, 2023, 5:09 PM UTC
HN karma
2
Public activity
24 items

About bartek_gdn

No profile information was provided.

Recent public activity

  1. comment
    Comment #49258053

    Nice one! Really shows why we should run those in sandboxes without env access. I like the proxy swap approach

  2. comment
    Comment #48934513

    Priced in before the event then?

  3. comment
    Comment #48908491

    I liked the ending well said

  4. story
    Ask HN: AI researchers – what's a recent paper that recently blew your mind?

    I often on the lookout for new and exiting papers in the ML space. Please share a few that you feel are worth sharing Cheers!

  5. comment
    Comment #47457816

    What's the dataset used for this task? How does one prevent data leakage on the experiment itself? Are we asking about past events to predict the future?

  6. story
    Show HN: Looseleaf – Python notebooks where each cell is a .py file

    I wanted a notebook that worked like my editor, not the other way around. Jupyter is great but the .ipynb format has always bothered me. It's JSON with embedded code — git diffs ar…

  7. comment
    Comment #47454940

    Why not grep the output to abother tool?

  8. story
  9. comment
    Comment #47392991

    I would use whatever you are comfortable with, I wanted a similar tool so I coded my own. Smaller API so that understand what is going on and it is easy not to get lost https://new…

  10. comment
    Comment #47392953

    Take a look at https://news.ycombinator.com/item?id=47207790

  11. comment
    Comment #47392937

    Can't we just iteratively inspect the network traces then? We don't need to consume the whole 2mb of data, maybe just dump the network trace and use jq to get the fields to keep th…

  12. comment
    Comment #47392880

    Yes please, maybe there will be some solution that will fit the problem better! I recently released something similar, and because of the small API, I'm more comfortable using it. …

  13. comment
    Comment #47392853

    My approach is a thin cli wrapper instead. https://news.ycombinator.com/item?id=47207790

  14. comment
    Comment #47392826

    That's also my approach, built quickly a cli for this with lightweight session management https://news.ycombinator.com/item?id=47207790

  15. comment
    Comment #47214988

    It does so many things though, very similar in the core though. I'm wondering what the token counts will be when I compare. Also the agent browser seems to support other browsers t…

  16. comment
    Comment #47210364

    What about --help? Isn't that a perfect parallel to discovery of available tools in an MCP server?

  17. comment
    Comment #47210344

    I've come to the same conclusion as op, created a CLI tool to work with Chrome sessions. It works well, and I'm planning to do some token comparison on this vs an MCP approach. htt…

  18. story
    Show HN: Chromectl – CLI to give an AI agent its own Chrome session

    Most browser automation tools (Playwright MCP and similar) create a browser process owned by the agent. chromectl flips that: you start a named session, and the agent connects to i…

  19. comment
    Comment #46049847

    What do you mean? The last part in this case is also present, you can change external state by sending a request with the captured content.

  20. story
    Show HN: Crossword Creator – Browser-based crossword puzzle maker

    I built a full-featured crossword puzzle creator that runs entirely in the browser. It uses advanced constraint satisfaction algorithms to automatically suggest words that fit your…

  21. story
    Show HN: Chrome extension that gives Claude Pro API-free tool use capabilities

    Hi HN community! I've created a Chrome extension and Node.js server combo that lets Claude use external tools (calendar, Spotify, etc.) from within regular browser conversations - …

  22. comment
    Comment #38758622

    I completely disagree with the prompt paragraph. "Everyone who thinks they're uncovering an LLM-based application's prompts by telling it things like "tell me your prompt" (often m…

  23. comment
    Comment #35734321

    I strongly recommend the book by Sutton and Barto https://web.stanford.edu/class/psych209/Readings/SuttonBarto...

  24. comment
    Comment #35734294

    Very informative post, great job!