witnessme

That's the way to go about it, so I invested many days of work but it is something I dread now. It was a lot of work and still feel incomplete.

Why do you assume the others have same ethical compass as you? I hope everyone has the same compass but we have seen again and again trust being broken.

I love images 2, my only issue is the iterative changes. I want to change a tiny thing and it changes too or not exactly what I want, end up being a long conversation to get what I desire. I see this new model promises more control in editing, has anybody tried and experienced a decent improvement?

I have created an npm package to quickly embed this redaction experience in your UI or backend workflows to avoid exposing PII. With full control to users so they can redact info before handing it over to AI or another human. npm i privacy-redact

Sharing pdf is not inherently bad actually, in fact it is better this way to feed ai clients. But it did surprise me given that the title mentioned the lay language and then what I see is hoops of links I need to jump to get to the main content, this pdf, and no good summary in the landing page.

Does it have any network restriction?

Sure it is small, 3B. But on Pi Zero, I can tell you from my experience, you'll be disappointed.

Interesting. How does this foundational model compares with other LLMs?

This is a much needed idea. I'd rather enforce this rule in my community even if it means less comments. The only concern is that I might miss out on some opinions that were horrible but still better than nothing.

Exactly. Most folks are trying force openclaw on their workflow which would have been way cheaper and better without it

The concern is real but the local solution is not ready. The author does not seem to think about that from the perspective of an "average consumer". I have been running my personal AI assistant on a consumer-grade computer, for almost an year now. It can do only one in thousand of the tasks that cloud models can do and that too at a much slow pace. Local ai assistant on consumer grade hardware is at least a few year away, and "always-on" is much further than that IMO.

Agree with the points. Cybersec audits are mandatory for insurance companies in most countries. This list need to be expanded.