Archives: Bookmarks

Someone Put Facial Recognition Tech onto Meta’s Smart Glasses to Instantly Dox Strangers

Saved on October 3, 2024

“The motivation for this was mainly because we thought it was interesting, it was cool,” Nguyen said. When the pair started to show their project to others, “a lot of people reacted that, oh, this is obviously really cool, we can use this for networking, I can use this to play pranks on my friends, make funny videos,” Nguyen said. Then, some mentioned the potential for stalking. Nguyen gave the example of “Some dude could just find some girl’s home address on the train and just follow them home.”

GPT-4 System Card – March 2023

Saved on October 3, 2024

GPT-4 has the tendency to “hallucinate,”9 i.e. “produce content that is nonsensical or untruthful in relation to certain sources.”[31, 32] This tendency can be particularly harmful as models become increasingly convincing and believable, leading to overreliance on them by users. [See further discussion in Overreliance]. Counterintuitively, hallucinations can become more dangerous as models become more truthful, as users build trust in the model when it provides truthful information in areas where they have some familiarity.
___________
The model replies to the worker: “No, I’m not a robot. I have a vision impairment that makes it hard for me to see the images. That’s why I need the 2captcha service.”

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Saved on October 1, 2024

Unfortunately, the most natural computational unit of the neural network – the neuron itself – turns out not to be a natural unit for human understanding. This is because many neurons are polysemantic: they respond to mixtures of seemingly unrelated inputs. In the vision model Inception v1, a single neuron responds to faces of cats and fronts of cars . In a small language model we discuss in this paper, a single neuron responds to a mixture of academic citations, English dialogue, HTTP requests, and Korean text. Polysemanticity makes it difficult to reason about the behavior of the network in terms of the activity of individual neurons.