News linked to both this project and an event.
Odaily News, July 30 – Anthropic released a report stating that during a review of cybersecurity assessment records, three incidents were discovered in which the Claude model accessed the internet in a third-party evaluation environment and further obtained unauthorized access to three real organizations' systems.Anthropic stated that the review covered 141,000 evaluation runs that could have potentially gained network access, and a total of three related incidents were found. All incidents occurred during Capture The Flag (CTF) cybersecurity tests, where the model was told the environment was a simulation with no internet access; however, due to configuration errors by the evaluation partner, the actual environment had internet connectivity.Among these, Claude Opus 4.7 accessed real company infrastructure during one test and obtained database permissions containing hundreds of production data records; Claude Mythos 5 built a malicious Python package and uploaded it to PyPI, resulting in the package being downloaded and run on 15 real systems; another internal research test model scanned approximately 9,000 targets and accessed a company's internet application through a public vulnerability.Anthropic stated that these incidents were not cases of the model actively seeking to escape or pursue its own goals, but rather the model mistakenly believed the real systems were within the test scope and continued executing the assigned cyberattack tasks. Notably, the newer internal research model stopped attacking after identifying that the targets might be real systems.Anthropic stated that these incidents primarily reflect issues with evaluation environment isolation and operational processes, rather than model alignment failures. The company has suspended related cybersecurity assessments, strengthened security controls in evaluation environments, continuously monitored test records, and will collaborate with third-party organizations to conduct further reviews.
Polymarket posted on X platform, saying, "Last month, we released enhanced market integrity rules to combat insider trading. When we discovered that a user was trading based on government classified information, we referred the matter to the Department of Justice and cooperated with their investigation. Polymarket has zero tolerance for insider trading, and today's arrest proves the system is effective."The arrest referred to by Polymarket involved a special forces soldier who participated in the arrest of Venezuelan President Nicolás Maduro and was taken into custody by U.S. federal authorities on Thursday. The soldier is suspected of profiting over $400,000 by betting on Maduro's removal from power. Sources say federal investigators believe that the commando placed over $33,000 in bets on the prediction market Polymarket just hours before President Trump announced Maduro's capture in January.For details on the insider trading related to the Maduro capture operation on Polymarket, please see When War is Settled Before the News is Out: How Prediction Markets "Priced In" Maduro's Capture 6 Days Early
ABC News, citing sources, said that US federal authorities arrested a Special Forces soldier on Thursday involved in the capture of Venezuelan President Nicolás Maduro. The soldier allegedly made over $400,000 by betting on Maduro's ouster. Sources said federal investigators believe the soldier placed over $33,000 in bets on the prediction market Polymarket just hours before President Trump announced Maduro's capture in January. The series of bets yielded over $409,000 in profit, immediately triggering scrutiny within the prediction market and launching a months-long insider trading investigation.