Pull requests are fixes or updates to current software program which are submitted for evaluation earlier than they go stay. They’re the bread and butter of software program improvement, the chunks of code that almost all skilled builders spend their lives writing—or did till now.
“Who right here has shipped a pull request that was fully written by Claude the place they didn’t learn the code in any respect?” Hadfield requested subsequent. Nervous laughter. Many of the arms stayed up.
It’s not information that LLM-powered instruments like Anthropic’s Claude Code and OpenAI’s Codex have upended the way in which software program will get made. Prime tech firms now prefer to boast of how little code their builders write by hand. (“Most software program at Anthropic is now written by Claude,” Hadfield mentioned. “Claude has written a lot of the code in Claude Code.”) OpenAI, Google, and Microsoft make comparable claims. Many others want they may.
Even so, it’s hanging how regular this new paradigm already appears, and how briskly it has set in. This was the second 12 months that Anthropic has placed on developer occasions, which additionally run in San Francisco and Tokyo. This time final 12 months, the corporate had simply launched Claude 4. It might code, type of. However with Anthropic’s newest string of updates—particularly Claude 4.6 after which 4.7, launched in February and April—Claude Code is a instrument that increasingly more builders appear pleased at hand their work off to.
ANTHROPIC (GRAPHIC) / WILL DOUGLAS HEAVEN (PHOTO)
Anthropic says its aim is to push automation so far as it’s going to go. As a substitute of utilizing AI to generate code after which having people clear it up and repair the errors, it needs Claude to test and proper its personal work. “The default isn’t ‘I’m going to immediate Claude’—the default is now ‘I’m going to have Claude immediate itself,’” Boris Cherny, who heads Claude Code, mentioned within the opening keynote.
If all goes effectively, human builders shouldn’t even see the error messages when one thing doesn’t work. That can all be dealt with by Claude, which is able to take a look at and tweak, take a look at and tweak, till all the pieces runs because it ought to. As Ravi Trivedi, an engineer at Anthropic, put it in one other speak: “The important thing precept is getting out of Claude’s manner. We prefer to say: ‘Let it cook dinner.’”
Trivedi offered a brand new characteristic in Claude Code, introduced two weeks in the past, which Anthropic calls dreaming. Claude Code brokers write notes to themselves, recording and saving helpful details about particular duties. When one other coding agent later begins to work on the identical code, it might probably use the notes to stand up to hurry sooner and be taught from any errors that earlier brokers might have made.
Dreaming is a system that Claude Code makes use of to learn via all these notes and consolidate the data they comprise, recognizing patterns and customary points throughout totally different duties. In idea, dreaming ought to assist Claude Code study a selected code base and get higher and higher at engaged on it.
