Stories

Show HN: ChatGPT You Can Teach

Article news.ycombinator.com

Show HN: ChatGPT You Can Teach

Hey HN! I'm Karthik & have been working on Typemagic (https://typemagic.com): a ChatGPT client that saves your prompts, and applies them when needed based on your chat.

The Problem: Since it came out, I've been using ChatGPT for various tasks, such as coding, generating database queries, reviewing my writing, and learning new things. Initially, I found myself constantly managing useful prompts in a Notion doc. I'd either paste a prompt from Notion to provide the right context or sift through my chat history to locate that context.

Some examples of snippets I frequently used include: - A detailed summary of my Tech stack. - Movie and book preferences (for suggestions). - My database schema (so that it could write queries). - Writing guidelines to follow when reviewing my writing.

This workflow was fine for 3 prompts, but sucked for 10. So I set out to build a better way.

Typemagic automatically searches for the best prompts in your library, applying them when needed based on your chat. Once you save your a prompt, you (hopefully!) don't have to worry about applying it manually - Typemagic takes care of it. While there's definitely room for improvement, this approach has been more effective than manually searching and pasting the right prompts for me.

I'd greatly appreciate any feedback you have, especially critical feedback :).

The Journey: This is the second iteration of the product. In the first version, you could create ChatGPT agents to chat with. But before asking what you wanted, you had to choose the right agent to chat with. Needing to make this decision every time you wanted to switch context was too much friction.

I realized my design approach was outdated. With AI, we have the opportunity to offload more decision making from users' minds onto AI. The right balance is one in which users act more as managers: approving / rejecting proposals, vs. actually, outright, deciding. As AI becomes more powerful, this balance will shift towards AI making more / most of the decisions.

With this insight, my friend Akash and I designed the current version that relies on Typemagic choosing the prompts during your chat while giving you visibility and control over the prompts applied.

Under the hood: Currently, Typemagic uses embeddings (https://platform.openai.com/docs/guides/embeddings) to find the best prompt matches by comparing your current chat embedding with the embeddings for all of your prompts to find the best matches.

Using Firebase, Firestore for auth and to store data. Deployed on Vercel (huge fan!).

What's Next? I'm working on enhancing the experience with faster performance, better recommendations, and the ability to share and discover useful prompts.

I'd greatly, greatly appreciate your feedback. Thanks for reading this far.

Discussion 0 comments · 4 points · koopuluri · 2023-06-17
Open on HN
Loading the discussion…

Domain filters

Stories from these domains are hidden from every list. Subdomains match too: blocking substack.com also hides danluu.substack.com.

    About YAVCHN

    YAVCHN is a reader for Hacker News and Lobsters, with articles and discussions in separate windows or Classic pages.

    Created by Paul Parks and built with PUDL.

    YAVCHN source code on GitHub

    Help

    Keyboard

    j / k
    Move down and up the story list. The arrow keys scroll whatever has focus.
    Enter
    Read the marked story in the article reader.
    ]
    Read the next story in the same article-reader applet. Back returns to the previous story.
    p
    Pin or unpin the marked story, which keeps it in Pinned.
    n / N
    Move to the next or previous top-level comment in the window in front.
    c
    Collapse or expand that comment.
    f
    Hide or show the story list.
    Esc
    Close a menu or this help.
    Access key m
    Go to the menu bar. Most browsers take it with Alt on Windows and Linux, and Safari with Control and Option.
    ?
    Show this help.

    Windows

    Each story opens in a window holding its article above its discussion; drag the bar between them to share the room differently. A window can be moved by its title bar, resized from any edge, snapped to a half or a corner by dragging it there, maximised, or minimised to the bar at the foot of the page. Use Window > New reader window to open an empty reader, or Story > Open in new reader window to open another reader for the current article. Docked readers keep their articles when you select another story from the sidebar. Minimized readers can be restored and reused for their site. A window's Next story link reads on down the list in the same window.

    A link in a comment or an article to another Hacker News or Lobsters thread opens that thread in a window too. A link to a single HN comment opens the comment above its replies.

    While a story's window is in front, the Story and Discussion menus in the menu bar hold its commands: pinning, Next story, sorting, collapsing every thread, jumping to the first new comment. Each window also remembers where you were in its article and discussion, so a reload, or Back to a story that Next took you past, finds your place again. Closing a window forgets it.

    The whole arrangement lives in the address, so a bookmark or a shared link brings it back, and Back undoes the last change. Moving between Hacker News, Lobsters, their lists, Pinned and Find changes only the list, and leaves the windows open.

    The list

    The pin at the start of a row keeps the story in Pinned, and the cross at its end hides it. Pinned can be narrowed by words in the title, site or author, by source, and to the stories you haven't opened yet, and ordered by when you pinned them, by points or by comments; the filters are part of the address, so a filtered view can be bookmarked. Scroll past the end of the list to load more. Domain filters, in the View menu, hide every story from a site.

    Browsing view

    View > Windowed and View > Classic select the browsing view and save your default in this browser. Window view reuses a reader for each feed. Classic view opens stories and applets as pages. Open as a page is a one-off action that does not change your saved default. Use the Windowed selector to return an article to a window. Direct page links always open as pages.

    Applets

    The Applets menu in the menu bar holds three tools, each a window of its own. Replies to me takes your Hacker News user name and lists the replies to your last thirty comments and stories, checking again every three minutes while it is open, and marking what is new since you last marked them read. Look up a user opens a profile on Hacker News or Lobsters, with their submissions and recent comments, as a commenter's name in any discussion does; the bar at the top of a profile looks up someone else in the same window, and Back returns to the one before. Who is hiring? filters the posts of HN's monthly hiring threads by the words you type.

    They read only what the sites publish to everyone, so none of them asks for a login, and your user name stays in this browser.

    Find

    Find takes any link and lists every time it was submitted to Hacker News and Lobsters, so you can read each discussion of it.

    About

    YAVCHN never sees your Hacker News or Lobsters login. The discussion is fetched from each site's public API; to vote or reply, follow the link above the discussion, or the arrow beside a comment, to the source's own site. Pins, hidden stories, filters and layout are kept in this browser only.

    Open source: github.com/paulmooreparks/yavchn. Built with PUDL.