Google wants to let robots write their own code
But the apocalypse isn’t here yet
When you purchase through links on our site, we may earn an affiliate commission.Here’s how it works.
Googlehas released an newopen sourcebenchmark that it says will allow robots to perform tasks by writing their own code in response to human-written instructions.
The company has launched a newwebsiteto reveal “Code as Policies” (CAP), whereby prompts written in plain English can be interpreted into language-model generated programs (LMPs) written in Python code.
CAP is the successor toPaLM-SayCan, a project that similarly allowed a physical helper robot to be directed through commands in plain English. CAP promises to allow for more complex tasks to be completed with increased accuracy, in part due to allowing machines to write their own code.
Self-coding robots
In ablog postdiscussing CAP’s release, Google Research Intern Jacky Liang and Research Scientist Andy Zeng describe the motivation for the technology, and what it might mean for the future.
“What if when given instructions from people, robots could autonomously write their own code to interact with the world? […] Given natural language instructions, current language models are highly proficient at writing not only generic code but, as we’ve discovered, code that can control robot actions as well.”
But it might not be the time to throw away yourlaptop for programmingjust yet. In testing, Google’s researchers demonstrated simple commands with a similar structure. Test robots were able to “draw a 5 cm hexagon around the middle” [of a whiteboard], and “put the blocks in a horizontal line near the top” [of a square boundary].
Check out our list of the best monitors for programming right now
Python programming libraries found hiding security threats
Inside the effort to refine one of the world’s most popular programming languages
In the accompanyingpaper, titled “Code as Policies: Language Model Programs for Embodied Control”, the project team concede that CAP currently doesn’t have the ability to deal with especially abstract or complex commands or perceive descriptions of trajectory. The team’s approach also didn’t account for impossible commands being fed though CAP.
Are you a pro? Subscribe to our newsletter
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
In theory, the open source nature of Google’s “robot-centric” implementation of LMPs in Python could result in much quicker implementation of solutions to these issues. The CAP website also containsreleasesvia Github, and an interactivedemovia Google Colab to describe how robots “write” code in response to commands.
Luke Hughes holds the role of Staff Writer at TechRadar Pro, producing news, features and deals content across topics ranging from computing to cloud services, cybersecurity, data privacy and business software.
7 myths about email security everyone should stop believing
Best Usenet client of 2024
I’m a die-hard Apple fan, but even I’ll admit that the Google Pixel 9 Pro is the best-looking phone of the year