Google’s new CodeMender autonomous agent was designed to automatically correct code flaws, taking cybersecurity against digital harassment and phishing a step further.

The DeepMind division is behind this AI agent, which is here to “revolutionize code security.” In the words of DeepMind researchers Raluca Ada Popa and John “Four” Flynn, the value of CodeMender is already palpable. “This system leverages Gemini’s reasoning capabilities to automatically identify flaws, generate patches, and automatically validate solutions before final human review.”

With this launch, Google reinforces its commitment to using AI to shift the balance of cybersecurity in favor of defenders. This is a sustained, long-term effort.

“We’re making this happen with the launch of CodeMender for autonomous defense, through strategic partnerships with the global research community through the AI ​​VRP, and with the expansion of our Secure AI Framework 2.0 to protect AI agents,” they added.

M.Pino

Source: wired

(Reference image source: Adarsh Chauhan en Unsplash)

Visit our news channel on Google News and follow us to get accurate, interesting information and stay up to date with everything. You can also see our daily content on X/Twitter and Instagram

La entrada Google launches CodeMender, an autonomous cybersecurity agent apareció primero en Bitfinance.