""" The attack on “silos” usually comes from people outside of a silo, generalists who don’t have deep disciplinary knowledge or focused training. These people don’t want their ideas validated by a community of experts. They find expertise to be inconvenient. The image of the silo as narrow, contained, a kind of ivory tower, seems to support the claim that those in them are narrow, out of touch, or secluded. """

The links in the first paragraph actually do quite a good job of explaining what people mean when they say Silos are bad. No one claims that disciplines and departments and teams should become a single blob. This article might be defending something that needs no defense and is not under any attack.

I did enjoy reading about the history of Silos :)

The nuances you've captured across so many different interfaces must've taken you a long time!

You need to consider the exploitative nature of something like this carefully. On the technical side, we understand the limitations of something like this, and that we'd never take it seriously. But what about people who don't understand the tech (which is most people)? What about children and teenagers?

I see from your comment history that it's possible the issues with this app and your previous "Free AI Girlfriend" website might be not be clear to you. I urge you to spend some time reading about this, it's very clear that you're talented and skilled. I wish you all the best!:)

Starting point reading material: https://www.spiegel.de/international/zeitgeist/artificial-in...

Looking forward to trying this out soon!

I also think more high level patterns would make Koreo more approachable. Real world problems and how they could be addressed with Koreo.

Also looking forward to reading through the SLSA for ML PoC and seeing how it evolves. I was planning to use Witness for model training but wasn't sure how it would work for such a long and intensive process.

I can talk for literally hours about how good it is when you connect it to your company's Confluence or Jira or Slack or Google Drive or a ton of other things. At a scale of many tens of thousands of documents too.

Their team is awesome too and completely tuned into exactly what their users need. And that it's open source is the cherry on top. No secret in how your data is being used.

- An incredibly happy user looking forward to more from Onyx

For a person with zero front-end knowledge, it's a game changer.

Also I don't think the two dependencies can be equated. Electronics create super short attention spans, books are the complete opposite. So I think she's already doing better than most her age.

All the breathless evangelizing out there is for incredibly simple problems that break down the second we try something complex. Yes a GPT-4 agent can go far in the coming months, but there's a ceiling to how good it can be because there's a ceiling to how well the model can reason. Newer LLMs will be the ultimate answer.

I eagerly look forward to the day this becomes stable. Looks like a project that will stick around for a long time, especially with the care being put into it.

Good luck team!