I'm currently building an internal tool using SurrealDB directly, but I'm curious to use Morphik since it implement features I hadn't the time to figure out yet. (For example, I started with hardcoded schemas and I like how you support both).
Minor nitpick, but the README for your ui-component project under ee says:
"License
This project is part of Morphik and is licensed under the MIT License."
However, your ee folder has an "enterprise" license, not the MIT license.
I also installed Tavily Search, sequential thinking, and Playwright.
I still use Cursor for development, and I use Claude Desktop for higher-level documentation, testing, etc.
For example, I'll check out a new repo that is lacking in documentation. I'll get the app running, then explain to Claude where the code lives, how to access the real app, and how I want the features documented.
Then Claude will happily scan the codebase, take screenshots of the running app, etc., all by himself, and then create a report (through the artifact system) with visualizations, graphs, etc.
Haven't had time to try it out, but I've built myself a tool to tag my bookmarks and it uses 3.5 Haiku. Here is what it said about the official article content:
I apologize, but the URL and page description you provided appear to be fictional. There is no current announcement of a Claude 3.7 Sonnet model on Anthropic's website. The most recent Claude 3 models are Claude 3 Haiku, Sonnet, and Opus, released in March 2024. I cannot generate a description for a non-existent product announcement.
I appreciate their stance on safety, but that still made me laugh.
Thanks for taking the time to explain your process. I'm just starting out, and so far I was planning to:
- Radar: just cool categorized articles, libraries, apps, etc. that I found during the week and organized in weekly drops.
- Guides: In my mind, those were closer to TIL than real guides, though I couldn't figure out how to name them. I love TIL for that.
- Playground: Forcing myself to share prototypes, snippets, etc.
I also have tons of LLM chats that could become content. Instead of trying to rewrite them, I will just share them as they are (while being transparent).
The main idea, as you said, is to find a modality that works well for me and force myself to write more.
1. My personal website. -> I spent so much time ingesting content, I finally realized I need to produce some too.
2. A AI assisted brief generator -> clients often have a hard time articulating their requirements for new projects.
3. Prototyping the UX of "my" version of the perfect "process aware" editor. More organized than a Wiki, more flexible than tools like Jira, Aha and all. Not ready to share a public link yet. My goal is share my mockup in a week or two.
Same here situation here (went from paid to free for a similar reason). We are a small team, so we don't represent a lot of $, but it's changed how I perceive Gitlab as a company, and it also means I won't recommend them anymore to clients.
I'm really impressed so far, it can either act as the only backend, or as an admin tool over an existing DB. It also has built-in support for "flows" to automate support tasks.
Funny, I was asking myself the same question this morning, I was wondering if there was the equivalent of SETI@Home but to pool resources for model training.
For your question specifically, the following explain it well I think:
..locating a previously found item on an extremely long page is inefficient, especially if that item is placed many scrolling segments down. It’s much easier for people to remember that the item is on page 3 than it is to gauge where the item is positioned on an extremely long page.