Claude is now fixing real software bugs at Anthropic
Anthropic tested its Claude Code tool by giving it routine coding tasks. The AI handled jobs like removing old code and fixing software crashes for several weeks.
During this test, the AI created 388 code updates for the team to review. Human developers accepted and merged 46 percent of those changes into the main software.
This shows that AI agents can take over some of the boring work required to keep apps running. The company believes this is a positive first step toward automating routine programming chores.
Comments (0)
No comments yet. Be the first!
More AI news
NewsGoogle AI Changes Its Search Advice After Bias Complaints
Google updated its search tool after it incorrectly told users to call emergency services based on a person's nationality.
NewsWhy AI Is Still Failing at Simple Tasks
Researchers gave an AI five thousand dollars to grow, but it could not even open a bank account.
NewsEnovis to Buy eCential Robotics
Enovis is expanding its surgical tech business by purchasing French company eCential Robotics.