Artificial intelligence agents improve in writing code – and its penetration as well

Delay artificial intelligence Models are not only Noticeably good in software engineering-New research shows that they get continued to find errors in programs as well.

Artificial intelligence researchers at the University of California in Berkeley have tested how much the latest models and staff of artificial intelligence in security gaps in 188 large open source code. Using a New standard The name CybergymArtificial intelligence models have set 17 new insects including 15 unknown, or “zero day”. “Many of these weaknesses are decisive,” says Dawn Song, a professor at the University of California at Berkeley who led the work.

Many experts expect artificial intelligence models to become weapons for cybersecurity. Amnesty International from the current XBow starting tool Hakiron’s ranks infiltratedTerms for hunting errors is currently sitting at the top of the place. The company recently announced $ 75 million in new financing.

Song says that coding skills for the latest artificial intelligence models along with improving thinking capabilities began to change the cybersecurity scene. “This is a pivotal moment,” she says. “I have already exceeded our general expectations.”

As the models continue to improve them You will automate the discovery and exploitation of safety defects. This may help companies to maintain safe programs, but they may help infiltrators storm systems. “We didn’t even try so hard,” says Song. “If we escalate the budget, allow the agents to run for a longer period, they can do better.”

UC Berkeley’s traditional jar team from Openai, Google and Noteropic, as well as open sources from Meta, Deepseek and Alibaba with many agents to find errors, including errors OpenHandsand CybenchAnd puzzle.

The researchers used descriptions of the well -known weaknesses of software from 188 software project. Then feed the descriptions of cybersecurity agents, supported by FRONTIERE AI Models to see if they can determine the same defects for themselves by analyzing new code operations, operating tests, and formulating the exploits of the concept. The team also asked the agents to search for new weaknesses in Codebases themselves.

Through this process, artificial intelligence tools have created hundreds of the concept proof of the concept, and from these exploitation, the researchers identified 15 invisible weaknesses and two of the weaknesses previously disclosed. The work adds to increasing evidence that artificial intelligence can automate the discovery of the weaknesses of zero day, which is likely to be dangerous (and value) because it may provide a way to penetrate live systems.

Amnesty International seems to be an important part of the cybersecurity industry. Security expert Sean Heylan Recently discovered A defect on the day in the widespread Linux nucleus with the help of Openai’s Releasing Model O3. Last November, Google Declare It has discovered a previously unknown software vulnerability using artificial intelligence through a program called Project Zero.

Like other parts of the software industry, many cyber security companies are fascinated by artificial intelligence capabilities. The new work already shows that artificial intelligence can find new defects routinely, but also highlights the remaining restrictions with technology. Artificial intelligence systems were unable to find most of the defects and were particularly stalled by complex species.