

For LLMs, sure, but there’s no way they’re running LLMs on-device. Just classic AI models at the most


For LLMs, sure, but there’s no way they’re running LLMs on-device. Just classic AI models at the most


Image element recognition doesn’t magically make actions happen, such as following a QR code link. The on-board AI would be more along the lines of pattern recognition such as reading text, license plates, people counts, etc. You could poison it by putting up the license plates but unless someone is actively looking for those plates it’ll just be a small bit of metadata attached to the time code. The fact that they’re stationary means it’ll probably be ignored as well


Highly unlikely that any amount of significant processing is happening on-device. Wouldn’t be cost effective


Shit! Why didn’t I think of that?


They fundamentally cannot fix hallucinations in LLMs


Which index is that?


To think that the guy that wrote Freeman’s Mind would go on to such heights. Proud of you, Ross.


Something like speckit is necessary to make big, sweeping changes that continue past the context window


I just found out about the AGPL’d Fluxer today


Can you DNS block the webos update site?


As always, there’s a clippy rule for that.
RIP the volt. I’m keeping mine until it dies but it’s a tragedy