Improving C++
March 15 2024C++ guru Herb Sutter writes about how we can improve the programming language for better security.
The immediate problem “is” that it’s Too Easy By Default™ to write security...
Read more
Burglars Using Wi-Fi Jammers to Disable Security Cameras
March 13 2024The arms race continues, as burglars are learning how to use jammers to disable Wi-Fi security cameras.
Read moreJailbreaking LLMs with ASCII Art
March 12 2024Researchers have demonstrated that putting words in ASCII art can cause LLMs—GPT-3.5, GPT-4, Gemini, Claude, and Llama2—to ignore their safety instructions. Research paper.
Read moreUsing LLMs to Unredact Text
March 11 2024Initial results in using LLMs to unredact text based on the size of the individual-word redaction rectangles. This feels like something that a specialized ML system could be trained on.
Read moreFriday Squid Blogging: New Plant Looks Like a Squid
March 9 2024Newly discovered plant looks like a squid. And it’s super weird:
The plant, which grows to 3 centimetres tall and 2 centimetres wide, emerges to the surface for as...
Read more
Essays from the Second IWORD
March 9 2024The Ash Center has posted a series of twelve essays stemming from the Second Interdisciplinary Workshop on Reimagining Democracy (IWORD 2023).
- Aviv Ovadya, Democracy as Approximation: A... Read more
A Taxonomy of Prompt Injection Attacks
March 8 2024Researchers ran a global prompt hacking competition, and have documented the results in a paper that both gives a lot of good examples and tries to organize a...
Read moreHow Public AI Can Strengthen Democracy
March 7 2024With the world’s focus turning to misinformation, manipulation, and outright propaganda ahead of the 2024 U.S. presidential election, we know that democracy has an AI problem. But...
Read more
Recent Comments