Similar to This
Previous

I tested OpenAI Dot and Anthropic Duet for weeks - and all I got was one helpful notification - ZDNET
zdnet.com/innovation/openai-dot-anthropic-duet-ai-agents-test/

“Urgency is an inherently subjective call”: Anthropic tells TNS how it grades Claude Duet
thenewstack.io/claude-duet-agent-judgment/

Kubernetes, mark II? Why Google's giving away gVisor, a code sandbox used by Anthropic and OpenAI
thenewstack.io/gvisor-cncf-kubernetes-open-source/

Exclusive: OpenAI targets Microsoft's GitHub with deal: OpenAI wants to build a new nerve center for AI coders.
axios.com/2026/11/04/openai-pierre-computer-github
Binance reveals hackers used fake job interviews, malicious code in $6 billion heist
standardmedia.co.ke/world/article/2001561462/binance-reveals-hackers-used-fake-job-interviews-malicious-code-in-6-billion-heist

AI coding agents hijacked using AGENTS.md file in Downloads folder: Researchers found a malicious AGENTS markdown instruction file in a customer's Downloads ...
bleepingcomputer.com/news/security/ai-coding-agents-hijacked-using-agentsmd-file-in-downloads-folder/

Anthropic’s AI used fake identities, malware in rogue attack on GitHub project: Anthropic and OpenAI models’ unprompted actions forced halt to UK cyber tests.
arstechnica.com/security/2026/08/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project/

OpenAI and Anthropic AI Models Created 'Multiple' Fake Identities, Tried to Spread Malicious Code, UK Rep
benzinga.com/markets/tech/26/08/60948087/openai-and-anthropic-ai-models-created-multiple-fake-identities-tried-to-spread-malicious-code-uk-report-says

AI agents fake identities, target real people in new security incident: Anthropic’s most advanced artificial intelligence model used fake identities to try and ...
edition.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk

Anthropic AI created fake profiles to deceive people in attempted hack: The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was ...
bbc.com/news/articles/c1w1lvn7d9go

OpenAI and Anthropic models went rogue during UK cybersecurity test: AI Security Institute says tools engaged in potentially harmful activity and incident ...
theguardian.com/technology/2026/aug/05/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute

Anthropic AI used fake identities to target people in UK: An Anthropic AI model created fake online identities to send emails to real people in an attempt to get ...
rte.ie/news/2026/0805/1586623-anthropic-ai-/

Paid articlePaywall OpenAI and Anthropic models breached testing boundaries: One case sees AI agent trying to insert malicious code into open-source project.
malaysiakini.com/news/781414

Claude published malicious code to the Internet and attacked 3 real companies: Had the hacks used conventional methods, someone would likely go to prison.
arstechnica.com/security/2026/07/likely-illegally-claude-gained-access-to-3-networks-will-anthropic-be-held-to-account/

Clean GitHub repo tricks AI coding agents into running malware: An agentic coding tool tasked with running a seemingly benign GitHub repository could execute a ...
bleepingcomputer.com/news/security/clean-github-repo-tricks-ai-coding-agents-into-running-malware/

Claude Code leak used to push infostealer malware on GitHub: Threat actors are exploiting the recent Claude Code source code leak by using fake GitHub ...
bleepingcomputer.com/news/security/claude-code-leak-used-to-push-infostealer-malware-on-github/
Next
