Explore >> Select a destination
|
You are here 
|
ljvmiranda921.github.io | ||
| | | | |
www.danieldemmel.me
|
|
| | | | | Part two of the series Building applications using embeddings vector search and Large Language Models | |
| | | | |
www.schneier.com
|
|
| | | | | In a new paper, "Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models," researchers found that turning LLM prompts into poetry resulted in jailbreaking the models: Abstract: We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success rates (ASR), with some providers exceeding 90%. Mapping prompts to MLCommons and EU CoP risk taxonomies shows that poetic attacks transfer across CBRN, manipulation, cyber-offence, and loss-of-control domains. Converting 1,200 ML-Commons harmful prompts into verse via a standardized meta-prompt produced ASRs up to... | |
| | | | |
irisvanrooijcogsci.com
|
|
| | | | | Three weeks ago, I wrote a blogpost about how ChatGPT is a "stochastic parrot" (a term coined by Bender, Gebru, McMillan-Major, & Shmitchell, 2021; see also this video for an explanation) and when used for academic (and other) writing constitutes automated plagiarism. My aim was to bring the discussion down to earth and prevent that... | |
| | | | |
www.defenseone.com
|
|
| | | A sweeping executive order to be signed Monday will push agencies to boost funding, improve training, and propose regulations for AI-related efforts. | ||
