I’ve actually talked with two other companies that are doing that rather than hiring people to convert things. Since it’s not asking the LLM to create code from scratch or a framework, apparently it works surprisingly well and then they have a dev, versed in a modern language go through it, and ensure it’s relatively sane. The quote I heard was “it’s really no different than picking up someone else’s code to look at”.

This is the best summary I could come up with:

For large organizations, it tends to be a complex and costly proposition, given the small number of COBOL experts in the world.

When the Commonwealth Bank of Australia replaced its core COBOL platform in 2012, it took five years and cost over $700 million.

Running locally in an on-premises configuration or in the cloud as a managed service, Code Assistant is powered by a code-generating model, CodeNet, that can understand not only COBOL and Java but around 80 different programming languages.

A recent Stanford study finds that software engineers who use code-generating AI systems similar to it are more likely to cause vulnerabilities in the apps they develop.

“Like any AI system, there might be unique usage patterns of an enterprise’s COBOL application that Code Assistant for IBM Z may not have mastered yet,” Puri said.

IBM sees a future in broader code-generating AI tools, as well — intent on competing with apps like GitHub Copilot and Amazon CodeWhisperer.

The original article contains 734 words, the summary contains 159 words. Saved 78%. I’m a bot and I’m open source!

Ibm replaces COBOL: Great idea

… with Java: Questionable idea

… using an LLM: Exceptionally bad idea