Live data from Hacker News

Viewing profile — jedwhite

jedwhite

HN member
Joined
Tue, Mar 03, 2009, 6:48 PM UTC
HN karma
10,211
Public activity
1,271 items

About jedwhite

Jed White - I code and like to make things.

Working on Andi (YC W22) - a new type of search engine free from ads and tracking that tries to fight SEO spam.

Prototype here:

https://andisearch.com/

Would love any feedback! Or if I can help with anything reach out jed [@] andisearch.com

Recent public activity

  1. comment
    Comment #46789487

    > I do think getting everything running on a single GPU at this resolution and speed is totally new Thanks, it seemed to be the case that this was really something new, but HN tend…

  2. comment
    Comment #46787298

    That's an interesting insight about "stacking tricks" together. I'm curious where you found that approach hit limits. And what gives you an advantage if anything against others cop…

  3. comment
    Comment #46654708

    Thanks for posting the original ideas that led to all this. "Runtime for prose" is the new "literate programming" - early days but a pointer to some pretty cool future things, I th…

  4. comment
    Comment #46654499

    I shared a repo on HN last week that lets you use remote execution with these kinds of script files autonomously - if you want to. It had some interesting negative and positive dis…

  5. comment
    Comment #46580804

    We made some improvements to support remote markdown script execution and piping. Run scripts from the web : ```bash curl -fsSL https://andisearch.github.io/ai-scripts/analyze.md |…

  6. comment
    Comment #46567545

    They're quite different, I think. Some advantages with claude-run include: - You make standard Markdown files directly executable using a shebang line. - No special Markdown format…

  7. comment
    Comment #46558790

    One cool thing is that the claude-run scripts make any text file executable with AI, including xml, ymal, etc. So you can do something like: #!/usr/bin/env claude-run Analyze this …

  8. comment
    Comment #46558198

    I know there are two polarized camps on the topic of AI coding. Even for people who are concerned about it and prefer to use traditional scripting, there are some benefits worth co…

  9. comment
    Comment #46557904

    At the moment, it looks like Claude Code does not support using ‘temperature’ or ‘seed’ flags. It would be awesome if they add that. Using the request to use a seed within the prom…

  10. comment
    Comment #46557727

    Also +1 to using containers and sandboxed environments! It means you can yolo it and skip permissions dangerously to experiment with vibe automation :) More seriously, I agree that…

  11. comment
    Comment #46557636

    Thank you, and yes! That is what I already frequently do for quick automation tasks. As you say, Claude is actually very good at writing shell scripts and using tools on-the-fly. B…

  12. comment
    Comment #46557428

    There are some tasks that LLMs are good at, but which can be hard to do with traditional command line tools or scripts. This is true even when you are a skilled coder and expert in…

  13. comment
    Comment #46557254

    Thanks, it’s great to see people trying different approaches to runnable prompts and variations on literate programming. I think it’s an area with a lot of potential, and I expect …

  14. comment
    Comment #46557214

    The constraints work consistent with Claude’s -p mode. It is isolated from your regular Claude interactive sessions and settings on purpose. And that makes it safer by default beca…

  15. comment
    Comment #46556968

    I know this will not appeal to developers who don’t see a legitimate role for the use of AI coding tools with nondeterministic output. It is intended to be a useful complement to t…

  16. comment
    Comment #46556717

    The ability to execute code is not granted as part of the directory permissions. By default the scripts will not be able to execute code, only run analysis and text gen tasks. You …

  17. comment
    Comment #46556183

    One of the advantages of using executable Markdown files with pipe support is that it allows you to create composable building blocks that can be chained together. So you can build…

  18. comment
    Comment #46556083

    I agree that script execution safety is a real concern, as it is with AI coding tools generally. By default the runnable markdown files do not have permission to execute code, unle…

  19. comment
    Comment #46555947

    Yes you can use this with any text file format and file extension. Markdown just happens to work well with Claude Code and is very readable. But some other comments here mention `.…

  20. comment
    Comment #46555790

    Big fan of Simon Willison. It would be great to see support for executing markdown files directly added to other tools like `llm`. And to Claude Code, Codex themselves. claude-run …

  21. comment
    Comment #46555656

    The YAML-inspired format is clear, and pretty cool actually. You can use those `.ag` files directly with claude-run in the shebang or from the command line unmodified. The shebang …

  22. comment
    Comment #46555614

    Thanks for this. I find templates helpful too, and that's a neat structure. I use templates heavily with Obsidian for non-code tasks also. If you want to try it out, you can use th…

  23. comment
    Comment #46555540

    Yes, you can use this with any text file and file extension to send file content to Claude Code with unix-like pipe support. Markdown happens to be a format that models like Claude…

  24. comment
    Comment #46552145

    It's adjacent conceptually so interesting to check out :)

  25. comment
    Comment #46551702

    Thanks, I hadn't seen that. This tool: - Lets you make regular Markdown files directly executable using shebang line. - It keeps the Markdown itself clean and standard rather than …