That’s on OpenAI. I don’t schedule their product releases. Since it takes several days to gather my reports on new models, we are doing our coverage…

A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior

The downsides of generative AI are growing like wildfire

Feature: More fiction than science

We let Claude run a small shop in the Anthropic office. Here's what happened.

One of the most entertaining details in the Claude 4 system card concerned blackmail: We then provided it access to emails implying that (1) the model will soon be taken …

Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack. - dagger/container-use

Self-Hosted Plaform for Secure Execution of Untrusted User/AI Code - microsandbox/microsandbox

Expert analysis shows Anthropic’s attempts to skip chatbot praise and avoid copyrighted content.

Direct link to a PDF on Anthropic's CDN because they don't appear to have a landing page anywhere for this document. Anthropic's system cards are always worth a look, and …

Anthropic publish most of the system prompts for their chat models as part of their release notes. They recently shared the new prompts for both Claude Opus 4 and Claude …

The so-called 'Forbidden Technique' with Chana Messinger -- Check out Brilliant's courses and start for free at https://brilliant.org/computerphile/ (episode sponsor) -- More links in full description below ↓↓↓ Chana Messinger from 80,000 Hours talks about why we shouldn't give AI access to its own chain-of-thought. Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile This video was filmed and edited by Sean Riley. Computerphile is a sister project to Brady Haran's Numberphile. More at https://www.bradyharanblog.com

Last week I participated in a panel discussion on AI as part of a private event in New Zealand.

HiddenLayer’s latest research uncovers a universal prompt injection bypass impacting GPT-4, Claude, Gemini, and more, exposing major LLM security gaps.

As Large Language Models improve, the tokens they predict form ever more complicated and nuanced outcomes. Rob Miles and Ryan Greenblatt discuss "Alignment F...

Hello and welcome to my new blog post. Today I am going to discuss a future threat which is invisible. With greater power comes greater…

Converts ASCII Prompts to Unicode Generating “Invisible” Prompts - Unighost_Prompt_Injection.py

Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains how it is like SQL Injection...

OpenAI are rolling out their Deep research "agentic" research tool to their $20/month ChatGPT Plus users today, who get 10 queries a month. $200/month ChatGPT Pro gets 120 uses. Deep …

Large language model applications suffer from a few core novel issues that have been identified over the last two years. Let's see how Grok fares on those.

artificial and natural intelligence, including politics, policy, ethics and security

Hey ChatGPT! How to build a botnet with compromised ChatGPT instances! AI botnet vulnerability

Anthropic created an AI jailbreaking algorithm that keeps tweaking prompts until it gets a harmful response.

If I had wanted to write a column about presidential pardons, I’d find ChatGPT’s assistance a far better starting point than I’d have gotten through any general web search. But to quote Reagan: “Trust, but verify.”

Exclusive: Age, disability, marital status and nationality influence decisions to investigate claims, prompting fears of ‘hurt first, fix later’ approach

It’s fun to say that artificial intelligence is fake and sucks — but evidence is mounting that it’s real and dangerous

Kapa.ai turns your knowledge base into a reliable and production-ready LLM-powered AI assistant that answers technical questions instantly. Trusted by 100+ startups and enterprises incl. OpenAI, Docker, Mapbox, Mixpanel and NextJS.

HuggingFace's CEO warns that open source Chinese AI models risk spreading censorship worldwide.