Fabric

Nice! You should integrate with github.com/danielmiessler/fabric!

You can also use the "fabric" CLI tool with its new "code_helper" functionality: https://github.com/danielmiessler/fabric?tab=readme-ov-file#... This is more rudimentary and works on the CLI, but I've had good results with it using both Gemini Pro and local models.

I think the person who wrote that probably meant these, specifically: https://github.com/danielmiessler/fabric/tree/main/patterns

I humbly submit my project as a possible solution. It's open-source on Github. https://github.com/danielmiessler/fabric The tagline is Human Augmentation Using AI, but really it's a crowd-sourced library of prompts. Basically, I solve a problem once, to a satisfactory level, and then I upload it to Fabric so everyone else can do the same. Over 22K stars just since January 2024.

For the queue management bit Fabric[0] seems like a decent idea, it's kind of trying to be a personal, private, local AI assistant. You feed it the stuff you'd normally read and it summarises it for you. Then you can decide which content you should spend more of your time on. Not nearly complete, but an idea I had even before I found out about it. And kinda similar what Apple is attempting with iOS18 and Apple AI. [0] https://github.com/danielmiessler/fabric

This setup is quite similar to the one fabric [1] patterns, the limitation i encountered while testing those with local llms was the prompt efficacy. More specifically the output format of the prompt is rarely respected properly. In addition to this the tone/sentiment of the answers vary a lot between models, as usual. Are there more compliant models wrt respecting prompt instructions? (assuming comparable parameter sizing) [1] https://github.com/danielmiessler/fabric

Pretty sure, web scraping has been upheld as legal when microsoft lost its case with companies scraping linkedin. And generative content is also legal, thats even includes reposting a copyrighted video even if there is discussion video over the video. Thats an extreme case of fair use, but it shows a wide use case over a copyright video. Personally been using fabric ai tool, since it can summarize youtube videos, so I dont have to watch an hour+ video or read a very long article/journal, just gives me a summary, top talking points or even break it down for tech points. https://github.com/danielmiessler/fabric

I'm a CLI dinosaur here. But is there a need of a 42.4MB animated logo gif for the GUI? https://github.com/danielmiessler/fabric/tree/main/images/fa...

People reinventing wheels at a pace never seen by mankind I dont see this mentioned enough: https://github.com/danielmiessler/fabric A location to track prompts for reuse by many people at the very least, specific tools including solving this exact same problem as well. Even though i am very skeptical of all the ai-bull at the very least it needs some kind of global cache database where people share prompts, input and output examples, and human tagged information on how it works or doesnt work. maybe even linked to real testing on why/if putting in "take a step back and look at the results" type nonsense does anything at all

Cool stuff! Maybe consider using (Fabric)[https://github.com/danielmiessler/fabric] as the templates for different prompts :)

Zero info on pricing on the page is unfortunate. Looks great. &Or make a longer demo video? --- Any opinion on Fabric? https://github.com/danielmiessler/fabric https://www.youtube.com/watch?v=lEXd6TXPw7E https://www.fabrichq.ai