SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks(arxiv.org)

42 points by amai 1 year ago | 15 comments

ArtPrompt: ASCII Art-Based Jailbreak Attacks Against Aligned LLMs(arxiv.org)

125 points by wut42 2 years ago | 35 comments

Solving Prompt Injection via Backtranslation(arxiv.org)

41 points by saliagato 2 years ago | 26 comments

Large language models in national security applications(arxiv.org)

74 points by bindidwodtj 1 year ago | 38 comments

Unsupervised Elicitation of Language Models(arxiv.org)

128 points by kordlessagain 1 year ago | 18 comments

UCSD: Large Language Models Pass the Turing Test(arxiv.org)

69 points by Mossy9 1 year ago | 80 comments

AI is just unauthorised plagiarism at a bigger scale(axelk.ee)

665 points by speckx 5 months ago | 542 comments

A personal blog post arguing that AI companies train on authors' work without consent or compensation, amounting to plagiarism at scale.

AI models can provably hide arbitrary capabilities(arxiv.org)

252 points by sbulaev 13 days ago | 118 comments

An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.

Loyal workers are selectively and ironically targeted for exploitation(sciencedirect.com)

341 points by ck45 3 years ago | 219 comments

Abstract page for a Journal of Experimental Social Psychology paper finding that loyal workers are selectively targeted for exploitation by managers.

The unexpected poetry of PhD acknowledgements(science.anu.edu.au)

339 points by zsrobinson 2 years ago | 78 comments

An ANU College of Science news article exploring the unexpectedly poetic and personal nature of acknowledgements sections in PhD theses.

Award-winning AI literature(jamesyu.org)

56 points by jamesjyu 4 days ago | 73 comments

A curated list of 33 literary awards since 2016 given to works where AI was used or suspected in the writing, grouped by allowed, confirmed, suspected, and withdrawn cases.

Computers Cannot Make Decisions(wiki.cateat.fish)

175 points by heavensteeth 16 days ago | 148 comments

A personal wiki essay arguing that blaming LLMs for harmful outcomes is decision laundering and that AI companies like OpenAI and Anthropic bear responsibility.