February 21-23, 2024
Montreal, Canada

Deepdive into Snyk Code - symbolic & neural AI

Symbolic techniques perform explainable predictions and the models are essentially immune to hallucinations. But, they require significant manual effort to scale (languages, frameworks, analysis & ruleset). Neural techniques are a promising new venture, however, their capabilities to discover bugs in code are limited by hallucinations and in the end are not significantly better than guessing. Let's combine them to overcome the shortcomings.

View all 171 sessions

Marcus Boerger

Snyk

Born in Germany, I worked for Google for over a decade as a C++ Staff Software Engineer, Uber Tech Lead and Tech Lead Manager. I am recognized as a PHP language designer and avid Open Source contributor. I have presented more than 50 talks and workshops at international conferences such as Confoo. Having worked in Australia for a few years, I moved back to Zurich where skiing is just closer.

Read More