Cue some story here on a bank or airline somewhere still relying on cobol backend servers.
These LLM conversions really seem to make modernization of large parts software layers possible!
Consider: You have a big mainframe running your tier 1 bank. Assume that you can see all the code on it, and you can feed all that to an LLM if you like. Getting it to spit out a Rust version is not what you actually want - you now have a modern language but it's still a singleton instance, so where do you run it? Most hardware doesn't give you enough uptime for what you need here, because what you actually needed was a re-architecture for distribution / failover / whatever, and while you could ask your LLM to do that you aren't going to run your bank on the result.
Why not?
I feel like we're entering a new era of prejudice against not a category of humans, but against non-human intelligences.
The design patterns for distributed and fault-tolerant systems are well-known and established in the industry. Both humans and AIs are familiar with them!
So if you sketch a design for the AI to follow, establish the rules in AGENTS.md, have a robust test suite, use a frontier model dialed up to eleven, etc... why not rely on the LLM output?
At the end of the day, humans are not without fault either.
I've been wading through some legacy "pre-AI" code recently and it has more bugs than a rainforest! Static fields used incorrectly, causing data races. Floating point types used for money amounts. JavaScript and SQL injection up the wazoo. Wildly unsafe password handling. So on, and so forth. This is the norm for most human-written software, not the exception.
As a proof-of-concept, I tried an AI rewrite of one such legacy app[1], and it is not bug free, but it notably has fewer bugs than the original. Different bugs, sure, and I'll have to iron them out after a round or two of UAT, but I'm honestly more confident with what I got from the chatbot than the code inherited from humans.
[1] Deals with money, but admittedly at a much lower level of risk and consequence than a banking app running on a mainframe.
What do you even mean by "works", specifically?
> it might have bugs, you know what they are.
Okay, so it doesn't work, you know it doesn't work, it's just that you accept the specific ways in which it doesn't work.
I've lost track of all the myriad stupid ways in which these ancient systems are hugely ineffectual without even being outright faulty.
Like airline tickets where your name is printed as "LASTFIRSTMR" in all caps and no spaces because their systems are ancient beyond belief.
Similarly, my bank statements are security-critical, because anyone with a copy of my credit card details can pull money out of my account without my express authorization. But...
... because they're stored in terrible ancient mainframe databases, the text fields all have tiny maximum lengths. Hence they're all abbreviations. Attacker-controlled abbreviations without any authenticity assurance of any kind!
I have no idea who actually transfers money out of my accounts! There are no URLs, no metadata, nothing to actually confirm the identity of the other party. Every field in a transaction record is 100% attacker-controlled and unverified by my bank.
If you look at it from the perspective of someone used to modern web security, then you realise that banking is a raging tyre in comparison. Banks literally just accept a certain rate of criminal activity and "price that in", reversing transactions when asked -- which itself can also be a criminal activity. They just shrug their shoulders.
"What can we do about this?" -- says the people that have tried nothing and are all out of ideas.
Rewrite it. The whole thing.
Use an actual database, something made in the last three decades instead of half a century ago.
Use cryptography. No, not crypto coins! I just mean a bog-standard algorithms like public-private key signing so that it is possible to confirm the source of transactions.
Etc.
I would much rather have something generated with the assistance of a modern LLM than what we have now, which is security holes big enough to drive a panamax container ship through.
It runs and accepts people's payments, which means you're not on the front page of the newspaper (not in a good way).
> ... because they're stored in terrible ancient mainframe databases, the text fields all have tiny maximum lengths. Hence they're all abbreviations. Attacker-controlled abbreviations without any authenticity assurance of any kind!
They also have to go through payment networks which are very often the limits on those things. So yeah, it sucks, but just fixing one DB isn't enough - the whole thing has to get upgraded.
> I have no idea who actually transfers money out of my accounts! There are no URLs, no metadata, nothing to actually confirm the identity of the other party. Every field in a transaction record is 100% attacker-controlled and unverified by my bank.
There is a little bit, but not much. Again, if these transfers are happening via card, it's all a terrible old fixed-length setup. Would be great if it was better, but you need Visa and Mastercard to upgrade as well. And of course there _is_ verification - most banks don't do a great job of surfacing this but they know if they've verified a PIN or CVC, or if it was contactless (in which case it _is_ unverified, but society realised we prefer the convenience there).
> Use cryptography. No, not crypto coins! I just mean a bog-standard algorithms like public-private key signing so that it is possible to confirm the source of transactions.
Obvious question then: You've made a card transaction. It is signed with the other party's private key. What does that buy you? How do you attach trust to this key? Whose is it - the payment gateway or the merchant?
> I would much rather have something generated with the assistance of a modern LLM than what we have now, which is security holes big enough to drive a panamax container ship through.
Sure, and if the LLM can rewrite enough of this system to get what you want, there's heaps of room for improvement. But this is orders of magnitude bigger in scope than rewriting your one old bit of COBOL software, it's systematic.
"It works if nobody attacks it." isn't security.
> They also have to go through payment networks which are very often the limits on those things.
For the same reasons.
> need Visa and Mastercard to upgrade as well.
They won't, and it's not worth asking them to. They're dinosaurs and will simply be replaced by a newer, more agile competitor.
It's already happening! Billions of people in Asia pay with their phones using home-grown payment systems, most of which are generally much more modern and better engineered.
> It is signed with the other party's private key. What does that buy you?
Same as what HTTPS does: attestation of identity by some trusted third-party, to some non-zero level. This could be literally just the existing CA networks and DNS domains as identity, but it could be governments, the banks themselves, etc.
I had some fraudulent transactions on my account labelled "Microsoft Subscription". It wasn't Microsoft. How can I tell?
Not even the bank knew the identity of the third party!
That's insane.
I feel like AI has dramatically changed how complete rewrites can be considered, especially for long-lived, legacy projects.
If only we had a way to solve these issues with tools capable of running Rust programs in that way. I guess every company that needs distribution / failover has a mainframe sitting in their office nowadays huh?
etc.
You could run one of these things on a mainframe, because it's a zero-downtime machine - you can swap out parts of them as they run. But fundamentally it's a singleton. It is deeply naive to believe you can trivially translate that to something running on Kubernetes just "because Rust".
Of course most companies that need distribution do manage to do that, and eventually the banks will get there too. But it isn't feasible to do that by translating their existing non-distributed COBOL code, they need a fundamental re-architecture, and that is much harder.
Sure you could keep vibe coding it but I wouldn't bet my data on that. A database needs to be rock solid.
Unfortunately that doesn't apply to all languages. LLMs are especially bad at producing code for the languages that were historically known as beginner-friendly as the training data was full of code by beginners doing what beginners do. All bets are off if you get stuck there. (Although maybe you could use an LLM to translate your code to a language that LLMs are good at!)
So either the translation produced Rust code in the "shape" of C code or the code is quite different from the C implementation.
Add to that that you need to have people proficient in Rust and also Postgres as well as the very much unknown codebase as a whole you get a recipe for pain.
There's existing money and expertise in those environments to rewrite the whole thing, yet they don't. You may loan them free engineers/experts and they might still not rewrite anything.
The existing system works. Yes, it costs a lot to maintain, and you could definitely reduce that if you moved to a more modern system. So now you're talking payback periods. Cost of development / maintenance cost savings per year = number of years before you pay back the project.
Problem is, that the cost of the development is often unclear, and the maintenance cost savings, while definitely above zero, and often unclear, and approximated the numbers usually come to a payback period in decades.
And that's without the usual tech caveats; We can't promise there won't be bugs. We can't promise deadlines will be met. We can't promise the project will succeed at all. We can't promise existing functionality will be faithfully reproduced in the new system. The normal risks around any software dev project.
All in all, it looks really expensive and really risky compared to just doing nothing and running the same old system for another five years.
Source: I helped do some of the maths on this for a Y2K project.
If the code is going to be translated forward instead of abandoned and then rewritten, as is now completely viable via LLM, there is no reason to move to a new language at all.
In 2026, not sure if it was satire. Do some people truly believe that all their software stack has to be single tech, from device drivers to end user apps? Does that extend to remotely accessed services?
I wonder if no one really thought there about rewrite that will still connect with all old dependencies with old protocols, but also will expose new kind of API that can be used by next rewritten block.
We also had mainframe, we used Oracle. It turned out that casual server is also reliable in long term and we restarted them only for upgrades of OS. Of course moving to some distributed, fault tolerant option also feels like good direction, but instead not-doing the perfect rewrite at once you can do it two/three step migration. Costs nowadays? You already fixed that.