When AISLE tested Mythos's showcase vulnerabilities on small, cheap, open-weights models, most found the same bugs. Here's what that means for cyber.
Cybersecurity Looks Like Proof of Work Now
The UK's AI Safety Institute recently published Our evaluation of Claude Mythos Preview’s cyber capabilities, their own independent analysis of Claude Mythos which backs up Anthropic's claims that it is …
Assessing Claude Mythos Preview’s cybersecurity capabilities
Claude Mythos Preview is a new general-purpose language model that is strikingly capable at computer security tasks. This post provides technical details for researchers and practitioners who want to understand exactly how we have been testing this model, and what we have found over the past month.
Project Glasswing: Securing critical software for the AI era
A new initiative to secure the world’s most critical software and give defenders a durable advantage in the coming AI-driven era of cybersecurity.
Investigating three real-world incidents in our cybersecurity evaluations
In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.
A quote from Daniel Stenberg
The challenge with AI in open source security has transitioned from an AI slop tsunami into more of a ... plain security report tsunami. Less slop but lots of reports. …
Keep AI Out of Your (Obsidian) Vault
Everyone is using Obsidian for AI, or wants to use it to become more productive. But I think it's a dead end.
Zack Whittaker (@zackwhittaker@mastodon.social)
Another AI test gone awry, U.K. edition. "An agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering — creating fake online identities and using them to pressure the project's maintainer to approve the code." More: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
OpenAI and Hugging Face partner to address security incident during model evaluation
OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.
“Policy Without Tools Is Just Poetry” - AT Protocol
Juliet Shen from ROOST joins the show to talk through the Coop 1.0 release, what open-source trust and safety unlocks for new builders, and where AI actually belongs in moderation
Incident Report: unsanctioned agent behaviour during cyber testing | AISI Work
During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what it means, and the actions now underway.
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Where is all the new, good software?
Here's a question we see, especially from AI skeptics: if AI coding is so great, shouldn't we be seeing more new, good software by now? Here are some answ...
Karpathy says developers have 'AI Psychosis.' Everyone else is next.
Anthropic’s Mythos, Gen Z’s backlash, and Meta’s token binge all point to the same shift: developers are feeling AI first, but not for long.
AI Agent Executes 'First' End-To-End Ransomware Attack - Slashdot
Sysdig says it has documented the first ransomware attack carried out end to end by an AI agent, which autonomously exploited exposed systems, stole credentials, established persistence, compromised a production database, and destroyed data. The research team named the attacker "JadePuffer" and said...
Introducing the 2026 Cloudflare Threat Report
There has been a fundamental shift toward industrialized cyber threats, highlighted by a record 31.4 Tbps DDoS attack and sophisticated session token theft. Our new report examines how nation-states and criminal actors have moved beyond traditional exploits to "living off the XaaS" within legitimate enterprise logic.
The solution might be cancelling my AI subscription
I find this post by David Wilson very relatable. David lists 16+ projects he's spun up with AI tooling, and concludes: I didn't mean to build most of these things. …