As the public conversation around AI has exploded, it's more important than ever for those of us driving development to critically reflect on what’s unfolding. I hope it’s useful. It intended to provoke debate and encourage everyone to develop new strategies for containment.
SAFETY
-
Bold GenAI Commitment Addresses Gray Area Ethics
By
–
This is a bold commitment related to one of the grayest areas of GenAI.
-
Was This Science Paper Written by LLM or Scientist?
By
–
Was the science paper written by a scientist or a LLM? https://
cell.com/cell-reports-p
hysical-science/fulltext/S2666-3864(23)00200-X
… -
Adobe Integrates Generative AI Safely Into Enterprise Products
By
–
I am having a great time at the #AdobeSummitEMEA – amazing to see how Adobe has integrated generative AI into their products in an enterprise-safe way. Find out for yourself: https://t.co/TKDPrIfDbh
— Bernard Marr (@BernardMarr) 8 juin 2023
#AdobePartner
@AdobeExpCloud pic.twitter.com/g3hlUGezFAI am having a great time at the #AdobeSummitEMEA – amazing to see how Adobe has integrated generative AI into their products in an enterprise-safe way. Find out for yourself: https://
lnkd.in/eHd6T8rP #AdobePartner
@AdobeExpCloud -
Stay Indoors Crisis Calls for Immediate Action
By
–
It is surreal. Everyone should stay indoors at this point. Definitely want this stuff gone.
-
New AI Detector Identifies AI-Written Content With 99% Accuracy
By
–
New Tool Can Tell If Something Is AI-Written With 99% Accuracy. A new study found an AI detector can detect AI-generated content in academic papers with a 99% accuracy rate. #GenerativeAI #OpenAI #ChatGPT https://
bit.ly/3P0mMrC -
AI Xenophobia: Historical Parallels with Moral Panic and Apocalypse Cults
By
–
Well-written pushback on AI xenophobia linking to precedents including “moral panic”, millenarian apocalypse cults, and Prohibition.
-
Reliability of Watermarks for Large Language Models
By
–
On the Reliability of Watermarks for Large Language Models paper page: https://
huggingface.co/papers/2306.04
634
… Large language models (LLMs) are now deployed to everyday use and positioned to produce large quantities of text in the coming decade. Machine-generated text may displace -
PromptBench: Evaluating LLM Robustness Against Adversarial Prompts
By
–
PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts paper page: https://
huggingface.co/papers/2306.04
528
… The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness -
Certified Reasoning with Language Models for Sound Step-by-Step Reasoning
By
–
Certified Reasoning with Language Models paper page: https://
huggingface.co/papers/2306.04
031
… Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, their reasoning can be unsound, inconsistent, or rely on undesirable prior assumptions. To tackle