ChatGPT is Fun, but the Future is Fully Autonomous AI for Code

ChatGPT and other AI tools based on Large Language Models (LLMs) have grabbed the headlines for their ability to write poems, short stories and other kinds of content – including code. The intuitive interactive interface makes them easy to use and they can be a real time-saver. LLM-based coding tools have begun to proliferate, with multiple options - like Copilot, Ghostwriter, and Codewhisperer - now available. But they all come with the same major drawback: the code they suggest is also often wrong in ways that can be hard to spot – so they require constant human supervision. But LLMs are not the only way to do 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. In this session we'll look at how LLMs and reinforcement learning approaches work, their pros and cons, what they are good at doing – and where they struggle, regardless of how much compute power you throw at them.


Mathew Lodge

CEO @Diffblue

Mathew is CEO at Diffblue, a pioneer of generative AI for code solutions. He has over twenty-five years of experience in the software industry in developer, product and marketing roles. Before joining Diffblue, Mathew's titles included SVP at Anaconda and Vice President of Cloud Services at VMWare. In each role, his focus has been building and marketing products that customers love.

Read more

Session Sponsored By

Diffblue Cover uses generative AI for Code to autonomously write complete Java unit tests that catch regressions sooner.


Wednesday Jun 14 / 01:40PM EDT ( 50 minutes )


Salon D


Video is not available


From the same track


Java for Serverless Cloud Functions: The How, Why and Tips to Make it Awesome

Wednesday Jun 14 / 11:50AM EDT

Developers have many options for building applications today, not just for what programming platform to use, but also what architectures are possible. Modern applications can be built using everything from monoliths to microservices to cloud functions.

Speaker image - Pratik Patel
Pratik Patel

Developer Advocate @Azul Systems.


Abstractions are Dead, Long Live Abstractions!

Wednesday Jun 14 / 10:35AM EDT

In modern app development, we have scripts that build and deploy servers, configure connectivity, monitor and report status, package and distribute code, observe activity across the system, and scale up or down as we need.

Speaker image - Alan Shreve
Alan Shreve

Founder & CEO @Ngrok