COBOL is just not a language typically talked about as a number one programming growth one, not less than not in 2023. That wasn’t all the time the case. COBOL, which debuted in 1959, was a number one language within the earliest period of computing and there are nonetheless billions of strains of COBOL code operating manufacturing functions in the present day.

Right now, IBM introduced a brand new initiative that makes use of the facility of generative AI massive language fashions (LLMs) to assist deliver COBOL functions into the trendy period. Among the many place that COBOL code continues to run is on IBM System Z (generally simply referred to a ‘Z’) mainframes. 

The brand new watsonx code assistant for Z service makes use of IBM’s watsonx LLMs for code growth to assist migrate COBOL software to extra trendy Java software code. By modernizing functions incrementally on the mainframe utilizing gen AI, IBM goals to assist purchasers deal with expertise gaps and make the most of Java expertise whereas decreasing threat.

IBM first detailed its watsonx product platform in Might throughout its Suppose convention as an effort to construct out a collection of basis fashions for AI, designed for enterprise use instances.

“We’re actually seeing the usage of generative AI for code help turning into a key use case and rising market traits,” Skyla Loomis, VP for IBM Z Software program, mentioned throughout a press briefing. “Generative AI will help builders to extra shortly assess, replace and check the fitting code.”

Why updating COBOL is vital 

A key problem with COBOL code is that there’s a shrinking base of builders that really know tips on how to keep it.

Loomis famous that roughly 84% of IBM’s Z mainframe purchasers are operating COBOL functions. As such, there’s a actual crucial to assist organizations modernize the code in a means that may be extra simply maintained. With the shortage of COBOL expertise, IBM took particular goal at coaching its AI so it may really perceive the traditional program language.

Within the press briefing, Kyle Charlet, CTO for IBM Z Software program, defined how watsonx code assistant was skilled to concentrate on COBOL code. Charlet mentioned that watsonx code assistant was initially skilled on CodeNet, one of many largest code information shops on the planet. Along with the CodeNet code, he famous that IBM can also be actively coaching and tuning the watsonx mannequin.

“Enterprise Z COBOL is the place we’re additional tuning that mannequin and handing it a bunch of COBOL Java pairs in order that it understands precisely tips on how to tune that mannequin,” he mentioned.

How generative AI transforms historic COBOL code into trendy Java

The watsonx code assistant can be utilized to investigate, refactor, remodel and validate COBOL functions using gen AI.

Charlet mentioned that the brand new providing can be utilized to “surgically extract” a logical enterprise service from a big monolithic COBOL software. The watsxonx code assistant can then be used to generate a Java class hierarchy and remodel the extracted COBOL code to Java. To validate the transformation, the answer generates automated assessments to make sure the brand new Java code is semantically equal to the unique COBOL.

Charlet defined that the watsonx code assistant is just not doing a line-by-line COBOL syntax translation to Java. That may result in COBOL syntax expressed in Java, he famous, which in his expertise is basically unreadable and unmaintainable. The IBM strategy is to take the intention of the COBOL code and map it into Java code that is smart.

“This Java needs to be recognizable and maintainable by Java professionals and fairly frankly, it’s,” mentioned Charlet.

Why code doesn’t lie or hallucinate, like textual content

A typical threat with gen AI know-how is that of hallucination, with outcomes that aren’t correct.

Whereas hallucination tends to be frequent downside with AI textual content era, Charlet argued that it’s much less probably with code generally for various causes. He famous that with the interpretation of human language and potential hallucinations, a person won’t acknowledge the hallucination as an error. Textual content is topic to interpretation by people, code nevertheless works considerably in another way than textual content.

Within the watsonx code assistant case, he defined that IBM validates the code that’s generated. The validation will instantly spotlight any hallucinations as a result of the code won’t run as anticipated if in any respect. As such, Charlet famous that whereas hallucination can doubtlessly happen with code era, these hallucinations should not a matter of opinion and may be recognized and corrected.

“Code doesn’t lie,” mentioned Charlet. ” Code is one thing that you simply observe and it’s a bunch of machine directions .”