AI-First Testing

Generative AI is accelerating development but how will it all be tested? GenAI is generating code all on its own, and like human developers–the generated code has bugs. GenAI is even fixing its own bugs and adding new features–without a developer in the loop. GenAI will soon generate 10X more code, and 10X faster–a 100X increase in the amount of software to be tested. The human-based approach to software testing just won’t scale.

Interestingly, GenAI can’t test the code it generates. Yes, it can generate unit tests, but it struggles testing larger systems, especially complex ones. You can’t put Amazon.com into a context window. The only way to test such complex systems is to test it–with AI. Only AI will be able to keep up with this coming tidal wave of code, risk, and complexity. AI-based testing isn’t just better, faster, or cheaper–it’s a necessity in the coming world of AI-generated code. Jason will walk through how these types of AI-based testing systems are defined, operated and scale. The future is near, and it is a world of AI testing AI-generated code..

Jason Arbon

Jason Arbon is the CEO of Checkie.AI, where his mission is to test the world's apps. Google’s AI investment arm led the funding for his previous company (test.ai). Jason previously worked on several large-scale products: web search at Google and Bing, the web browsers Chrome and Internet Explorer, operating systems such as WindowsCE and ChromeOS, and crowd-sourced testing infrastructure and data at uTest.com. Jason has also co-authored two-books How Google Tests Software and App Quality: Secrets for Agile App Teams.