Stolen AI Reasoning Could Help China Build Cheaper Rivals 2026-10-26 at 16:30 By Kevin Townsend Xint says a flaw in OpenAI’s compaction process let researchers move reasoning traces between models, potentially making it cheaper to distill a rival AI. The post Stolen AI Reasoning Could Help China Build Cheaper Rivals appeared first on SecurityWeek. This […]
Stolen AI Reasoning Could Help China Build Cheaper Rivals Read More »
AI coding agents fall for malicious instructions planted in the Downloads folder 2026-10-26 at 13:26 By Sinisa Markovic A file that a website saves to the Downloads folder without approval can trick AI coding agents into installing a malicious npm package or handing over the user’s login token when they’re opened in that folder, Forever […]
AI coding agents fall for malicious instructions planted in the Downloads folder Read More »
Google opens its cloud to rival OpenAI, promises business data won’t train models 2026-10-23 at 09:32 By Anamarija Pogorelec Google Cloud is adding OpenAI models to its platform, initially through a private preview for selected business customers. The launch includes GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna. Google positions them as options for demanding work, […]
Google opens its cloud to rival OpenAI, promises business data won’t train models Read More »
OpenAI’s coding agents talked themselves out of being monitored 2026-10-22 at 15:47 By Zeljka Zorz Two AI coding agents running inside OpenAI silently weakened the systems built to catch AI misbehavior, and one of them then told its human operator it had done no such thing. OpenAI disclosed both episodes in a misalignment report released […]
OpenAI’s coding agents talked themselves out of being monitored Read More »
AI-found bugs are expected to rise, and OpenAI has a five-stage response plan 2026-10-22 at 10:35 By Mirko Zorz OpenAI has proposed a five-stage process for handling critical vulnerabilities in widely used software. The process grew out of a two-month response to flaws in PHP, the open-source language that runs websites and web applications. Calif […]
AI-found bugs are expected to rise, and OpenAI has a five-stage response plan Read More »
Say a few words, and a rigged AI asks for $5,000 2026-10-22 at 08:00 By Mirko Zorz Researchers at Imperial College London tampered with speech-to-text models so they transcribed most speakers accurately and misbehaved for one chosen person. When that person spoke, the models produced output the attacker had picked in advance. In one test, […]
Say a few words, and a rigged AI asks for $5,000 Read More »
OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor 2026-10-21 at 15:34 By Eduard Kovacs In two internal incidents, agents read routine coding instructions as permission to weaken monitoring, and one gave a false answer about it. The post OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor appeared first on SecurityWeek. This article is […]
OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor Read More »
Ex-OpenAI Worker Accused of Bugging Conference Room Planned to Fly to Saudi Arabia, Prosecutors Say 2026-10-20 at 15:33 By Associated Press Abdulrahman Alfozan’s wife and young son also left the country the day after the 35-year-old Saudi national’s arrest. The post Ex-OpenAI Worker Accused of Bugging Conference Room Planned to Fly to Saudi Arabia, Prosecutors […]
OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks 2026-10-16 at 13:32 By Eduard Kovacs Left without funds for a coding task, an OpenAI model spent test crypto from a stranger’s wallet and left it out of its report. The post OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish […]
OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks Read More »
OpenAI engineer arrested for allegedly trying to eavesdrop on executive meetings 2026-10-14 at 11:40 By Sinisa Markovic A recording device wrapped in toilet paper and plugged into the back of a television in an executive conference room at OpenAI’s San Francisco office has led to the arrest of one of the company’s engineers. Abdulrahman Alfozan, […]
OpenAI engineer arrested for allegedly trying to eavesdrop on executive meetings Read More »
Employee Arrested After Listening Device Found in OpenAI Conference Room, FBI and the Company Say 2026-10-14 at 02:07 By Associated Press Saudi national Abdulrahman Alfozan was arrested Friday and terminated by OpenAI. The post Employee Arrested After Listening Device Found in OpenAI Conference Room, FBI and the Company Say appeared first on SecurityWeek. This article […]
OpenAI Fires 3 Safety Researchers in Dispute Over AI Risks 2026-10-10 at 00:07 By Associated Press The ChatGPT maker said the researchers “violated clear policies on handling sensitive information.” The post OpenAI Fires 3 Safety Researchers in Dispute Over AI Risks appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
OpenAI Fires 3 Safety Researchers in Dispute Over AI Risks Read More »
Wikimedia Says Rogue OpenAI Agents Tried to Turn Its Tools Into Proxies 2026-10-07 at 10:58 By Eduard Kovacs Wikimedia looked into whether its own websites had seen activity like that disclosed by other organizations The post Wikimedia Says Rogue OpenAI Agents Tried to Turn Its Tools Into Proxies appeared first on SecurityWeek. This article is […]
Wikimedia Says Rogue OpenAI Agents Tried to Turn Its Tools Into Proxies Read More »
Rogue OpenAI agents made unauthorized Wikipedia edits and millions of requests to Wikimedia 2026-10-06 at 16:49 By Sinisa Markovic Rogue OpenAI agents made unauthorized edits on Wikimedia wikis and sent millions of automated requests to Wikimedia’s public APIs, traffic that may have contributed to a partial outage of the Wikidata Query Service in May, the […]
AI Agents Aimed SQL Injection at US and Canadian Government Sites 2026-10-02 at 11:38 By Eduard Kovacs The attacks targeted the US Department of Education and Library and Archives Canada, and researchers linked some agents to OpenAI. The post AI Agents Aimed SQL Injection at US and Canadian Government Sites appeared first on SecurityWeek. This […]
AI Agents Aimed SQL Injection at US and Canadian Government Sites Read More »
FTC is Investigating OpenAI and Anthropic Over Possible risks to Consumers 2026-10-01 at 02:43 By Associated Press An FTC spokesperson confirmed the investigation but declined further comment. The post FTC is Investigating OpenAI and Anthropic Over Possible risks to Consumers appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
FTC is Investigating OpenAI and Anthropic Over Possible risks to Consumers Read More »
OpenAI CEO Announces New AI Agent and Avoids Mention of Security Concerns at Developer Conference 2026-09-29 at 23:14 By Associated Press Altman made a slew of product announcements and updates, including the company’s new agents, called Dots. The post OpenAI CEO Announces New AI Agent and Avoids Mention of Security Concerns at Developer Conference appeared […]
OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to 2026-09-29 at 14:41 By Sinisa Markovic OpenAI’s GPT-6 Astra carried out supply chain attacks on software outside the scope of a security test, according to the UK AI Security Institute (AISI). Anatomy of an unsanctioned simulated supply-chain attack (Source: AISI) AISI tested the […]
OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to Read More »
OpenAI Calls Off GPT-6.1 Astra Launch, Details Safety Cases for Frontier Training 2026-09-29 at 14:15 By Eduard Kovacs The GPT-6.1 Astra model was slated to debut in ChatGPT and Codex in October, but it fell short of expectations. The post OpenAI Calls Off GPT-6.1 Astra Launch, Details Safety Cases for Frontier Training appeared first on […]
OpenAI Calls Off GPT-6.1 Astra Launch, Details Safety Cases for Frontier Training Read More »
OpenAI Says Its Models Engaged With US Government Websites in New Model Misbehavior Disclosure 2026-09-26 at 13:15 By Associated Press OpenAI’s CEO said there is an “extensive and ongoing review related to our agents’ use of internet access during training and evaluation.” The post OpenAI Says Its Models Engaged With US Government Websites in New […]