[DISCUSS] IBM using LLMs to convert COBOL to Java
[DISCUSS] IBM using LLMs to convert COBOL to Java
IBM's new product offering, Code Assistant for IBM Z, leverages a generative AI model to translate COBOL code to Java.
It's not the 1st time a language/tool will be lost to the annals of the job market, eg VB6 or FoxPro. Though previously all such cases used to happen gradually, giving most people enough time to adapt to the changes.
I wonder what's it going to be like this time now that the machine, w/ the help of humans of course, can accomplish an otherwise multi-month risky corporate project much faster? What happens to all those COBOL developer jobs?
Pray share your thoughts, esp if you're a COBOL professional and have more context around the implication of this announcement 🙏
You're viewing a single thread.
Not a cobol professional but i know companies that have tried (and failed) to migrate from cobol to java because of the enormously high stakes involved (usually financial).
LLMs can speed up the process, but ultimately nobody is going to just say "yes, let's accept all suggested changes the LLM makes". The risk appetite of companies won't change because of LLMs.
Wonder what makes it so difficult. "Cobol to Java" doesn't sound like an impossible task since transpilers exist. Maybe they can't get similar performance characteristics in the auto-transpiled code?
COBOL programs are structured very differently from Java. For example; you can’t just declare a variable, you have to add it to the working storage section at the top of the program.
That example doesn't sound particularly difficult. I'm not saying it'd be trivial, but it should be approximately as difficult as writing a compiler. Seems like the real problem is not a technical one.
It's never been a technical reason, it's the fact that most systems still running on COBOL are live, can't be easily paused, and there's an extremely high risk of enormous consequences for failure. Banks are a great example of this - hundreds of thousands of transactions per hour (or more), you can't easily create a backup because even while you're backing up more business logic and more records are being created, you can't just tell people "hey we're shutting off our system for 2 months, come back and get your money later", and if you fuck up during the migration and rectify it within in hour, you would have caused hundreds/thousands of people to lose some money, and god forbid there was one unlucky SOB who tried to transfer their life savings during that one hour.
And don't forget the testing that needs to be done - you can't even have an undeclared variable that somehow causes an overflow error when a user with a specific attribute deposits a specific amount of money in a specific branch code when Venus and Mars are aligned on a Tuesday.
What.
Most cobol systems have more code that doesn’t do anything vs code that actually does something.
The grammar of COBOL + shit UI of mainframes means there is a shit ton of tribal anti pattern with each program. It is a pia to add fields and variables, so lazy programmers would just reuse something that wasn’t being used at that instant. Less work and more job security.
What values do variables ROBERT1, ROBERT2 and ROBERT3 hold? Whatever ROBERT wanted.
The reason why these things still exist is business laziness. They don’t know and don’t care what cobol is or isn’t doing.
I am struck by … conversion to … Java? Really??? lol.
Most cobol systems have more code that doesn’t do anything vs code that actually does something.
What values do variables ROBERT1, ROBERT2 and ROBERT3 hold? Whatever ROBERT wanted.
And when that system is storing high-risk and/or sensitive data, do you really want to be the person who deletes code that you think "actually does nothing", only to find out it somehow stopped another portion of code from breaking?
The reason why these things still exist is business laziness. They don’t know and don’t care what cobol is or isn’t doing.
That's the thing - tor a risk-averse industry (most companies running COBOL systems belong here), being the guy who architected the move away from COBOL is a high-risk, high-stress job with little immediate rewards. At best, the move goes seamlessly, and management knows you as "the guy who updated our OS or something and saved us some money but took a few years to do it, while Bob updated our HR system and saved a bunch of money in 1 year". At worst, you accidentally break something, and now you have a fiasco on your hands.
Org change vs vertical integration, which is worse and why in 500 words or less ;)
Pay now or pay later…the organization is going to get kicked in the nuts.
For industries that have the option, companies who got kicked in the nuts ten yrs ago are doing better today than those who are still waiting.
IBM should shoulder a lot of the blame, there really is no reason why COBOL couldn’t be phased out in place except it would hurt IBM market share so it is not exactly a “thing”. In place transition to RUST should just be another section of the zOS manual.
Translating it isn't the difficult part. It's convincing a board room full of billionaires that they should flip the switch and risk having their entire system go down for a day because somebody missed a bug in the code and then having to explain to some combination of very angry other billionaires and very angry financial regulators why they broke the economy for the day.
Well, I'd rather the day be sooner than later. Also, this is why you have... Backup servers and development environments. You don't just flick the Switch randomly one day after code is made. You run months and months of simulated transactions on the new code until you get an adequate amount of bugs fixed.
There will come a time when these old COBOL machines will just straight die, and they can't be assed to keep making new hardware for them. And the programmers will all die out too. And then your shit out of luck. I'd rather the last few remaining COBOL programmers help translate to some other long lasting language before they all kick the bucket and not after.
Well, I'd rather the day be sooner than later.
Agreed, but we're not the ones making the decision. And the people who are have two options: move forward with a risky, expensive, and potentially career-ending move with no benefits other than the system being a little more maintainable, or continuing on with business-as-usual and earning massive sums of money they can use to buy a bigger yacht next year. It's a pretty obvious decision, and the consequences will probably fall on whoever takes over after they move on or retire, so who cares about the long term consequences?
You run months and months of simulated transactions on the new code until you get an adequate amount of bugs fixed.
The stakes in financial services is so much higher than typical software. If some API has 0.01% downtime or errors, nobody gives a shit. If your bank drops 1 out of every 1000 transactions, people lose their life savings. Even the most stringent of testing and staging environments don't guarantee the level of accuracy required without truly monstrous sums of money being thrown at it, which leads us back to my point above about risk vs yachts.
There will come a time when these old COBOL machines will just straight die, and they can't be assed to keep making new hardware for them.
Contrary to popular belief, most mainframes are pretty new machines. IBM is basically afloat purely because giant banks and government institutions would rather just shell out a few hundred thousand every few years for a new, better Z-frame than going through the nightmare that is a migration.
If you're starting to think "wow, this system is doomed to collapse under its own weight and the people in charge are actively incentivized to not do anything about it," then you're paying attention and should probably start extending that thought process to everything else around you on a daily basis.
When you say it like that... God bless America this whole system is doomed.
Nah, dump it all.
COBOL programs don’t handle utf8 and other modern things like truly variable length strings.
Best thing to do is refactor and periodically test by turning off the mainframe system to see what breaks. Why something was done is lost to the sands of time at this point.