[mentalgear]

It looks like a nice marketing product, but nowhere it acknowledges how bad LLMs are in general for summarization, or what techniques, if any, the devs use to counteract this. (also, their dev page https://orgsoft.org/ claim "NO BS", but again does not provide details, proof, not even an about page or a business address which is a red flag.

[mattvr]

Hey, thanks for the critique (this is my product)! Yeah, LLM summarization definitely has its challenges. We've actually spent months optimizing for this:

1. Using latest models (gpt-4o & claude-3.5) which show major improvements in quality

2. Extensive prompt engineering focused on distilling surprising insights vs. pure summarization

3. Structured output format that's easier to parse

Re: transparency - you're right, we need to add more details. I'm new to this and still learning how to communicate this.

Btw, it's free to use 1x/day, and here's an example: https://nuggetize.com/n/claude-shannon-wikipedia-47ca5e5b