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. However, the code LLMs write 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.


Speaker

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’s AI automatically writes complete Java unit tests that catch regressions sooner

 

Date

Tuesday Mar 28 / 11:50AM BST ( 50 minutes )

Location

Westminster (4th Fl.)

Share

From the same track

Session

Pipeline Patterns for Platform Teams

Tuesday Mar 28 / 02:55PM BST

 

Speaker image - Zan Markan

Zan Markan

Senior Developer advocate @CircleCi

Session

How ING Accelerated Kubernetes Deployments Across 500+ Applications: Challenges & Lessons Learned

Tuesday Mar 28 / 01:40PM BST

 

Speaker image - Wouter Ligtenberg

Wouter Ligtenberg

Sr. Engineering Manager @ING Hubs Romania

Session

Streaming Events? You Should Be Storing Them

Tuesday Mar 28 / 10:35AM BST

Event-driven architecture has been on many developers' minds for some time. Event streaming has increased in popularity, and whilst streaming has fantastic advantages, if you are not storing events at the source of the application, you are missing out on so many opportunities.

Speaker image - Yves  Lorphelin

Yves Lorphelin

Head of Developer Advocacy & Consultancy @Event Store

Speaker image - Matt Macchia

Matt Macchia

VP of Engineering @Event Store

Session

It's time to talk about your Big Code problem!

Tuesday Mar 28 / 05:25PM BST

Developer experience in the Age of Big Code: Today, every company has seen an explosion in the amount of code that they are dealing with compared to just 10 years ago. This leads to ‘The Big Code Problem’.

Speaker image - Mark	 McCauley

Mark McCauley

Field CTO @Sourcegraph

Session

InfoQ - Ask an editor

Tuesday Mar 28 / 04:10PM BST

An informal session for InfoQ editors and QCon attendees to connect, ask questions, and share ideas.

Speaker image - Daniel Bryant

Daniel Bryant

Platform Engineer, Co-Author of "Mastering API Architecture", Java Champion, and InfoQ News Manager