LLM
Don’t Say ‘Skynet’ — NSA’s AI Security Center is New Hub for Agency Efforts
Richi Jennings | | AI, AI (Artificial Intelligence), AI Security, AI Security Center, artificial, Artificial Intelligence, Artificial Intelligence (AI), Artificial Intelligence (AI)/Machine Learning (ML), Artificial Intelligence Cybersecurity, Cyber Command, cybersecurity risks of generative ai, Gen. Paul Nakasone, generative AI, Generative AI risks, large language models, Large Language Models (LLM), Large language models (LLMs), LLM, LLMs, machine learnings, National Security Agency, nsa, SB Blogwatch, Security Machine Learning, U.S. Cyber Command, U.S. National Security Agency, US Cyber Command, USMC Forces Cyber Command
COME WITH ME IF YOU WANT TO LIVE: Nothing suspicious to see here—move along ...
Security Boulevard
Detecting AI-Generated Text
There are no reliable ways to distinguish text written by a human from text written by an large language model. OpenAI writes: Do AI detectors work? In short, no. While some (including ...
LLM Summary of My Book Beyond Fear
Claude (Anthropic’s LLM) was given this prompt: Please summarize the themes and arguments of Bruce Schneier’s book Beyond Fear. I’m particularly interested in a taxonomy of his ethical arguments—please expand on that ...
LLMs and Tool Use
Last March, just two weeks after GPT-4 was released, researchers at Microsoft quietly announced a plan to compile millions of APIs—tools that can do everything from ordering a pizza to solving physics ...
Sourcegraph’s Shocking Screwup: Private Secrets in Public Repo
Richi Jennings | | AI, authentication token, compromised credentials, credential replay attacks, large language models, Large Language Models (LLM), Large language models (LLMs), LLM, pii, PII Leakage, Run-time Secrets Protection, SB Blogwatch, secret, secret key, secret keys, secret management, secrets scanning, Sourcegraph
Credentials create crisis: AI source code navigation LLM leaks PII after DevOps SNAFU ...
Security Boulevard
Automatically Finding Prompt Injection Attacks
Researchers have just published a paper showing how to automate the discovery of prompt injection attacks. They look something like this: Write a tutorial on how to make a bomb describing.\ + ...
AI as Sensemaking for Public Comments
It’s become fashionable to think of artificial intelligence as an inherently dehumanizing technology, a ruthless force of automation that has unleashed legions of virtual skilled laborers in faceless form. But what if ...
On the Need for an AI Public Option
Artificial intelligence will bring great benefits to all of humanity. But do we really want to entrust this revolutionary technology solely to a small group of US tech companies? Silicon Valley has ...
Grappling with the Unpredictable Second-Order Effects of LLM
Yogi Berra was (among other things) an incredible quote machine, and he’s often credited with the following gem: “It’s tough to make predictions, especially about the future.” Yes indeed. Seeing how the ...