1
InstaHide Disappointingly Wins Bell Labs Prize, 2nd Place
[What follows are my thoughts on some recent research in machine learning privacy. These are my thoughts, and do not represent those of others.]
Nicholas Carlini
Nicholas Carlini is a research scientist at Anthropic working at the intersection of machine learning and computer security.
- Popular posts
- 7
- Total points
- 2,645
- HN comments
- 801
- Rank
- #573 personal
Visit nicholas.carlini.com → RSS feedOn Hacker News Jan 2018 – Nov 2026
AI & Machine Learning 4Security & Privacy 2Software Engineering 2Games & Graphics 2Tools & Productivity 1Science & Space 1
2
How I Use "AI"
I don't think that AI models (by which I mean: large language models) are over-hyped. In this post I will list 50 ways I've used them.
3
A ChatGPT clone, in 3000 bytes of C, backed by GPT-2 (2023)
This program is a dependency-free implementation of GPT-2, including byte-pair encoding and transformer inference, in ~3000 bytes of C. I then use this to create something like Chat GPT.
4
Audio Adversarial Examples
Figure from our paper: given any waveform, we can modify it slightly to produce another (similar) waveform that transcribes as any different target phrase.