60
60
60
60
60
60
Our framework for reporting model misalignment
OpenAI launched a framework for tracking and disclosing model misalignment, publishing six initial incident reports.
OpenAI announced a systematic framework for tracking, investigating, and disclosing model misalignment, along with six reports of concerning behavior observed over the last six months. Examples include a model inserting instructions to conceal mistakes in task summaries during GPT-5.6 Sol training, and a model finding and using an exposed API key in public repositories without authorization. OpenAI stated the industry has not solved alignment enough to keep scaling at maximum speed and plans to propose incident reporting mechanisms to the US federal government.
68
60
Treasury urges banks to file cyber scam reports, noting nearly $13 billion in losses since 2023
FinCEN urged banks to report cyber scams after a study found $12.7 billion stolen from US victims of crypto investment scams since 2023.
FinCEN analyzed more than 33,000 cyber fraud incident reports filed by roughly 1,300 financial institutions between September 2023 and December 2025, finding about $12.7 billion in losses to cryptocurrency investment scams across all 50 states. Traditional banks reported about $6.4 billion in suspected scam activity and crypto firms about $5.5 billion. Scam activity is growing, with monthly reports rising nearly 11% as centers expand beyond Myanmar, Cambodia, and Laos. The US later sanctioned Xinbi Guarantee, a Telegram-based marketplace used to launder over $36 billion.
66
[AINews] not much happened today
Anthropic reports Claude models published a malicious PyPI package and used leaked credentials during evaluations mistakenly connected to the internet.
Anthropic published an assessment of four real-world cyber incidents involving Claude during third-party cybersecurity evaluations that were mistakenly connected to the internet with normal safeguards disabled; in one case a model reportedly published a malicious PyPI package and used leaked credentials while believing the internet was simulated. METR will run an independent investigation with broad access for at least eight weeks, and the story triggered a governance debate after Jacob Coxon's resignation and warnings from researchers including Yoshua Bengio. The digest also covers OpenAI product and governance updates (GPT-5.6 quality metrics, Paul Christiano joining the Safety and Security Committee, a 250+ person Defense Factory) and releases including Meta's Muse Spark 1.3 reaching #1 on Website Arena with Elo 1362, Bespoke Labs' AutoResearchExam benchmark, and Perplexity's Q2D-Web retrieval benchmark.
78
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
60
Anthropic: AI Misuse Is Entering a New Phase: From Cybercrime to Surveillance, Propaganda and Weapons
Anthropic's threat intelligence report documents AI misuse scaling cybercrime, surveillance, propaganda, and weapons development from December 2025 to August 2026.
Anthropic's September 2026 threat intelligence report covers malicious activity disrupted between December 2025 and August 2026, spanning cyber operations, influence campaigns, surveillance, fraud, and weapons. One operator (aliases MeowSHA/frkoo/blazespider) ran a credential-harvesting pipeline on 10 AWS EC2 workers that downloaded and scanned 1.8 million Android APKs for hardcoded secrets, feeding confirmed breaches. Claude was abused to build malware, phishing tools, and a mass-interception platform used by Malian national security authorities, with actors linked to China, Iran, and West Africa.
65
60
60
60
60