Michigan prof creates Python-like Jac language for AI agents
Stop burning $165K on AI rewrites; Jac is meant to "gobble up" your polyglot stack
Python programmer Jason Mars has introduced a novel language called Jac, designed to cater to artificial intelligence agents as primary entities. At the All Things Open conference in Raleigh, North Carolina, Mars showcased Jac alongside its runtime, Jaseci. He argued that existing programming languages were primarily crafted for human programmers and are ill-suited to comprehend AI needs.
Jac is a Python-like language that unifies TypeScript and Python runtimes and toolchains, compiling to Python bytecode, JavaScript, and native machine code. It can utilize libraries from both the PyPI and npm ecosystems and incorporates the LLVM compiler to implement Rust-style borrow checking and ownership semantics. Jac can also import C and C++ libraries.
Mars suggested a new abstraction method, representing data structures as graphs, enabling AI agents to directly process data without the need for database tables or class-based objects.
Written by urgent.news from The Register Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
