Code is a system of signals, set of instructions or symbols written in a programming language for communication.
Called Code Llama, Meta’s new publicly available tool aims to help programmers write more robust and well-documented software. It has the potential to make workflows faster and more efficient for developers and lower the barrier to entry for people who are learning to code, Meta said in a statement on Thursday.
It can generate code and natural language about code, from both code and natural language prompts.
Large language models are type of generative AI that can imitate human intelligence. They can distinguish, review, translate, forecast, and produce new content – text, audio or visual – using large data sets.
“We believe an open approach to AI is best for developing new AI tools that are innovative, safe and responsible, so we are releasing Code Llama for both research and commercial use,” Meta said.
“Code Llama features enhanced coding capabilities … it can also be used for code completion and debugging,” it added.
Generative AI could add nearly $4.4 trillion annually to the global economy and will transform productivity across sectors with continued investment in the technology, according to a new study by consultancy McKinsey.
Programmers are using large language models to perform various tasks. These models help them to be more efficient by avoiding repetitive tasks.
Meta said Code Llama is designed to support software engineers in various sectors, including research, industry, open source projects, NGOs and different businesses.
Earlier this week, Meta launched an AI-powered translation engine that can translate languages across text and speech.