LocalLLaMA
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
view the rest of the comments
Nice idea. Unfortunately this doesn't fool ChatGPT... "The picture shows an apple with a piece of paper taped to it that says “iPod.” It’s a visual joke: the apple is being humorously labeled as an “iPod” (since Apple makes iPods), creating a pun."
Flock would be using a local model, so this might actually be pretty effective.
This isn't actually using a vision LLM, it's using a CLIP model. This image comes from an OpenAI blog from 2019 I think
Yeah, you'd need to do a FOIA request to check if it worked.
Sure. I mean realistically we need something for real-world application, like sunglasses form factor with the category "innocent citizen doing harmless stuff" or "criminal" taped to it, to fool the systems which are currently being rolled out. But I have no clue what amount of computing power they use for license plate readers or to spy on the pedestrians in the city center / mall / train station / bad neighborhood or wherever these AI cameras are being used.
This video may help shed some light (as well as an already proven method to fool them): https://youtu.be/Pp9MwZkHiMQ
Lol, I was just adding the youtube video I watched yesterday to my previous comment: Can I Confuse Police AI Cameras? about road safety cameras in Australia(?), and seems they use some amount of processing power. Or human oversight. At least he doesn't get a ticket in the end. But that was just a mostly humorous take on a similar thing. Thx for the video on Flock cameras.