ChatGPT is fun, but the future is fully autonomous AI for code

ChatGPT and other AI tools based on Large Language Models (LLM) have grabbed the headlines. The intuitive interactive interface makes them easy to use and they can be a real time-saver. However, the code LLMs write is also often wrong – in ways that can be hard to spot – so they require constant human supervision.

LLMs are not the only way to do generative AI for code: fully autonomous code-writing is possible by using reinforcement learning to write code that is guaranteed to compile, run, and be correct.

Agenda

• Learn why the tech behind LLMs is good for some tasks but not others, and how reinforcement learning (RL) differs

• See how RL can write Java code completely autonomously

• Listen to the Q&A where we respond to attendee questions on these topics