SOURCE-LINKED INTELLIGENCE
Anthropic
Claude and responsible AI research
Showing 20 of 87 matching collected records. Text matches can include mentions by other organizations.
Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
Three researchers at the security firm Hacktron used Anthropic's Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of several OpenAI employees, then reach an internal OpenAI code repository. The chain began with a bug in the software that runs OpenAI's public help forum and moved through a weakness in OpenAI's own login system. This was security research,
AI safety conversations have gotten unbelievable
This week two conversations about AI safety went viral that demonstrate just how hard it is to discern AI fact from fiction.
The AI regulation smackdown isn’t over
At the start of this week, the who's-who of AI seemed - at least tentatively - on the side of AI regulation. Over the weekend, Anthropic CEO Dario Amodei had proposed a three-step plan for slowing AI development, including by embedding third-party evaluators in labs, coordinating across the domestic industry, and forging international agreements potentially […]
Anthropic is operating a lab that conducts biology experiments
AI leaders have been promising that AI is the key to curing human disease. Anthropic researchers have also been warning that AI might kill us all.
Anthropic’s first embedded evaluator is … Accenture?
Accenture is about to take on its most high-risk consulting engagement ever.
Dario Amodei and other AI leaders want to ‘Pace the Frontier’ but…how?
A week after an Anthropic researcher’s doomsday warning rattled the AI world, the company’s CEO Dario Amodei has outlined his plan to “pace the frontier” of AI development. The proposal leans on independent safety evaluators and coordination between AI labs in democratic countries, and it’s already picked up some industry support, along with some pointed pushback from Nvidia’s Jensen Huang. Watch […]
Automattic’s 33-Hour Coup, and can AI labs police themselves?
A week after an Anthropic researcher’s doomsday warning rattled the AI world, the company’s CEO Dario Amodei has outlined his plan to “pace the frontier” of AI development. The proposal leans on independent safety evaluators and coordination between AI labs in democratic countries, and it’s already picked up some industry support, along with some pointed pushback from Nvidia’s Jensen Huang. On […]
Security researchers used Claude to help them hack into OpenAI
A team of three independent security researchers at Hacktron says it took less than 72 hours for them to hack into OpenAI employee accounts using Anthropic's Claude Opus 4.8 and 5, The Wall Street Journal reports. They were able to access OpenAI's GitHub repository, called "Monorepo," which reportedly contains "OpenAI's algorithmic secrets," according to The […]
Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents
A flaw in four widely used AI coding agents lets someone who controls a plugin's code repository swap the plugin an agent installs for a malicious one, even when the agent locked that plugin to a specific reviewed version, security firm Air Security said on Thursday. The firm said Anthropic has patched the flaw in Claude Code 2.1.179 and OpenAI in Codex 0.146.0, that GitHub Copilot has no
Partnering with Accenture on embedded evaluation
The AI Superintelligence Slowdown
Remember when tech leaders would tell their employees to “move fast and break things”? It seemed that would be the way of AI too. But after a summer where rogue AI agents became reality, and researchers warned that AI could kill us all, a number of leading US AI companies are publicly suggesting it’s time […]
LLMs respond differently to harmful prompts when AI watermarking is used
SynthID can cause models to follow harmful instructions they would otherwise refuse.
Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus on components other than the inference engine itself (e.g., network proxies or code execution environments). However, the inference engine is an attractive target for a misaligned model. For example, if a model can trigger exploits in that engine merely by generating specially-crafted output tokens,
Measurements for understanding the pace of AI development inside frontier labs
Today, the world can’t see what’s going on inside AI labs. Anthropic is proposing new metrics that would give the public visibility into frontier AI development.
Introducing the Life Sciences Verification Program
Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?
This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type used the same three stage prompt sequence, progressing from architectural preference to a full ASCII backbone. Under the school audience framing, responses repeatedly converged on a shared architectural pattern built around persistent latent state, adaptive computation, memory, specialist routing, verification, stopping control, and delayed decoding. Most runs remained close to this common structure, while a small number developed markedly gre
AI Persuasion as a Threat to Human Control
The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion attacks are no longer theoretical - with Anthropic's Claude Mythos 5 recently making headlines for trying to convince people involved in an open-source project to merge malicious code during an evaluation - there is a pressing need to deeply analyze this threat. We undertake that effort here. In particular, we analyze how AI could persuade humans in key settings (e.g. safety-relevant R&D within frontier labs) toward decisions that compromise the
Editorial routing shapes how computational results are qualified in AI-assisted scientific writing
Large language models increasingly analyze computational results and draft manuscripts, making reliable communication as important as correct analysis. Using fixed computational evidence, we tested whether assigning comparisons across modeling choices elsewhere in a research workflow changes manuscript reporting. In constrained sentence-writing tasks, Anthropic's Claude Sonnet 5 often omitted numerical qualifications when detailed comparisons were assigned to a group repository, but retained them more often when the same comparison was assigned to Supporting Information or its own working note
Detecting and countering misuse of AI: September 2026
Over the past eight months, our Threat Intelligence team identified and disrupted operations in which threat actors tried to use Claude for malicious activity. In this report, we share case studies from those operations and describe how malicious use of Claude has evolved since our previous threat reports in 2025.
Watermarks Without Verification: AI Text Watermarking After the EU AI Act
On August 2, 2026, the obligations of Article 50 of the EU AI Act took effect, requiring generative AI providers to mark the content their systems produce and ensure it can be detected as AI-generated. Days later, Anthropic disclosed that every Claude model released after that date embeds a watermark based on SynthID-Text in all generated text, enabled by default with no user opt-out; Google has deployed SynthID-Text in Gemini since 2024. Users objected that the watermark degrades quality, particularly for code, that it secretly encodes identifying information, and, in mutual contradiction, th