client
Meltdown
client | Meltdown | |
---|---|---|
7 | 3 | |
351 | 9 | |
2.3% | - | |
9.2 | 10.0 | |
2 months ago | 2 days ago | |
Elm | Python | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
client
-
Show HN: I built a non-linear UI for ChatGPT
Interesting take! It does seem to address a typical "intermediate" workflow; even though we prefer linear finished products, we often work by completing a hierarchy first. I've been using Gingko [1] for years, I find it eases the struggle of organizing the structure of a problem by both allowing endless expansion of levels, and easily collapsing it into a linear structure.
In your case, do you hold N contexts (N being the number of leaves in the tree)? Are the chats disconnected from each other? How do you propose to transition from an endless/unstructured canvas to some sort of a finished, organized deliverable?
1: https://gingkowriter.com/
- Show HN: Structpad: notepad-database hybrid that helps you use abstract thinking
- How do you organize homeschooling and what software tools do you use
-
Forgotten program: Note taking or writing app where you can deep dive into words like a wiki, each one opening further and further to the right...
In re-reading your post, it occurred to me that you might also want to look at parallel/ horizontal outliners like gingko https://gingkowriter.com/ or https://gingkoapp.com/ (there was talk of a desktop app) https://wavemaker.co.uk/blog/wavemaker-version-3-is-live Evergreennotes https://evergreennotes.com/ (I believe it is inspired by https://andymatuschak.org/ technique). speare.com and https://transno.com/ and https://innos.io are similar in look and feel (same development team I believe)
- A different approach to note-taking and research
-
How to keep track of/plan writing?
I haven't used this on a document as large as the final PhD manuscript, but I feel like it might be helpful to you: https://gingkowriter.com/
- Treesheets app: cross-platform, free-form data organizer d
Meltdown
- Show HN: I built a non-linear UI for ChatGPT
- Interface for local and remote LLM models
-
Ask HN: Where can I find practical comparative data regarding different LLMs?
I'm also learning. The models get more accurate when they have more parameters, say 7b (7 billion parameters) vs 8x7b (56 billion parameters). They also take more time and resources at higher parameters. TheBloke at Huggingface uploads quantized models, which means they can run on lower spec computers but with a possible hit on quality, he offers multiple configurations per model depending on what you prefer. Big models can be too heavy and slow, the sweet spot is probably something like 13b. You can try different gguf models with this program: https://github.com/madprops/meltdown
What are some alternatives?
treesheets - TreeSheets : Free Form Data Organizer (see strlen.com/treesheets)
catwiki - CatWiki is a simple wiki that stores its articles as text files
manuskript - A open-source tool for writers
leo-editor - Leo is an Outliner, Editor, IDE and PIM written in 100% Python.
lobster - The Lobster Programming Language
mindforger - Thinking notebook and Markdown editor with LLM wingman.
TiddlyWiki - A self-contained JavaScript wiki for the browser, Node.js, AWS Lambda etc.