> A computer worm is malware that spreads on a network by replicating itself… more
~security×
60 links
> According to the Financial Times report, published on Wednesday, researchers… more
May 7: OpenAI starts a new training run for an experimental, unreleased model.… more
> In a talk that was a last-minute addition to the Black Hat security… more
> According to a joint alert from the FBI and the Environmental Protection… more
> By the time the agent escaped its sandbox and found Tailscale, it had already… more
> In the last two milestones, Chrome 149 and 150, we have fixed 1072 security… more
> After reviewing 141,006 evaluation runs where Claude could have obtained… more
> Security experts have been sounding the alarm for years about the risks of… more
> Ever since Anthropic kick-started a national conversation about the… more
> Over roughly two and a half days inside our infrastructure, an autonomous AI… more
> The first result we describe in this post, which was discovered with Claude… more
> OpenAI’s public disclosure, on July 21, that one of its agents had slipped… more
> All of this went down far too fast for a human-driven response. The only way… more
> Introducing honeyprompt, an LLM-first deception framework made by/for web… more
> This incident occurred during an internal evaluation which prompts models to… more
> Microsoft Corp. today released software updates to plug at least 570 security… more
> Severe cybersecurity vulnerability disclosures (CVEs) spiked in 2026. In… more
> The US government Friday lifted its block on Anthropic’s powerful Claude… more
> OpenAI said in a Friday blog post announcing its latest artificial… more
> Having spent the past year building small projects with Claude, I realized… more
> The Instagram accounts for the Obama White House and the Chief Master… more
> Recently, after I pointed out that Mythos only found a single low severity… more
> So far, Mythos Preview has found what it estimates are 6,202 high- or… more
> It's a different kind of tool doing a different kind of work, and that makes… more
> There has been something of a revolution in AI-based security research, and… more
Vulnerability Discovery and Exploit Generation: For the first time, GTIG has… more
> Just a few months ago, AI-generated security bug reports to open source… more
> A week ago the Copy Fail vulnerability came out, and Hyunwoo Kim immediately… more
> [...] We evaluate AgentFlow on TerminalBench-2 with Claude Opus 4.6 and on… more
> As we wrote in the Project Glasswing announcement, we do not plan to make… more
> Mythos Preview has already found thousands of high-severity vulnerabilities,… more
> A hacktivist group with links to Iran’s intelligence agencies is claiming… more
> Here's yet another troubling story about this "golden" era of AI. A hacker… more
> Anthropic’s team got in touch with Firefox engineers after using Claude to… more
A "benign payload" but installing openclaw doesn't seem benign to me... more
> Google on Friday unveiled its plan for its Chrome browser to secure HTTPS… more
> Prompt injection is a key problem in building reliable, long-running agents.… more
> New research shows that behaviors that occur at the very lowest levels of the… more
> We examine the extent to which security against a fully malicious server… more
> Google DeepMind and GTIG have identified an increase in model extraction… more
> The FBI has been unable to access a Washington Post reporter’s seized iPhone… more
> I had just accidentally social-engineered my own human. She approved a… more
Since this article was written, they renamed Moltbot to OpenClaw. more
> Introducing co-do.xyz [Source] - a demo and an experiment (with no… more
ssh sends lots of "chaff" packets more
> Recently I ran an experiment where I built agents on top of Opus 4.5 and… more
> Introducing Confer, an end-to-end AI assistant that just works.
> We developed a multipurpose secret-using service called the Tokenizer.