Skyramp is emerging from stealth with $10 million in funding and design partners like Box and Intel. Can its automated testing improve AI-generated code? Not everyone's convinced.
I totally get the skepticism from some oft he folks you mentioned. But I also think this team is onto something. I like that they are not leveraging the same LLMs to build the tests. It gives the software a new independent perspective. Plus, over time, ideally, you’d want this piece of software to identify and potentially fix all the errors. But for now, being able to “smell test” the code and quickly return the results with 90-95% confidence, will already be a massive help to the developers who are slowly expanding their “vibe code” use cases.
I totally get the skepticism from some oft he folks you mentioned. But I also think this team is onto something. I like that they are not leveraging the same LLMs to build the tests. It gives the software a new independent perspective. Plus, over time, ideally, you’d want this piece of software to identify and potentially fix all the errors. But for now, being able to “smell test” the code and quickly return the results with 90-95% confidence, will already be a massive help to the developers who are slowly expanding their “vibe code” use cases.