Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

news.ycombinator.com

Post reply on HN
Print view View original

31–40 of 60 posts

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#31

Post by wiz21c »

> The goal is to build digital “twins” of the experts on how they debug, architect, and maintain these systems in practice.

Sounds great but... I have migrated a big cobol codebase several years ago. Knowledge stored in the experts is 1/ very wide 2/ full of special cases that pop up only a few times in a year 3/ are usually complex cases involving analysing data, files which are on paper, etc. I strongly doubt an AI will be able to spot that.

The knowledge that usually misses the most is not "how is that done", because spending a few hours on COBOL code is frankly not that hard. What misses is: "why". And that is usually stored in laws, sub-sub-laws, etc. You'll have to ingest the code and the law and pray the AI can match them.

So in the end the AI will make probably 50% of the effort but then you'll need 150% to understand the AI job... So not sure it balances well.

But if it works, well, that's cool because re-writing cobol code is not exactly funny: devs don't want to do it, customers do it because they have to (and not because it'll bring additional value) and the best outcome possible is the customer saysing to you "okay, we paid you 2mio and the new system does the same things as before we started" (the most likely outcome, which I faced, is "you rewrote the system and its worse than before). So if an I can do it, well, cool.

(but then it means you'll fire the team who does the migration which, althgouhg is not funny and not rocket science, requires real expertise; it's not grunt work at all)

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#32

Post by sai18 »

huevosabio wrote: post #17

Cool! I think this is a great use of LLMs. The only other player I've seen is Mechanical Orchard

Mechanical Orchard is a major player in this space, though their model is closer to professional services than a true end-to-end AI modernization platform.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#33

Post by sai18 »

iepathos wrote: post #19

I can tell they're using MkDocs for the HyperDocs static site gen based on the screenshot. I'm working on an open source solution to generating docs with AI for codebases and maintaining them for documentation drift. I wrote a bit about it initially here https://entropicdrift.com/blog/prodigy-docs-automation/ for anyone who is interested. I'm currently using mdbook instead of mkdocs, may add support for a mkdocs work…

There’s a live playground you can try out here: https://hyperdocs-public.onrender.com/ — built just for the HN crowd.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#34

Post by sai18 »

mkoubaa wrote: post #30
brightball wrote: post #26

Earlier quoted context omitted.

Really good money in it for people who want to learn COBOL though.

Good money elsewhere for people capable of (a) learning COBOL (b) being effective in a legacy codebase and (c) operating in a large organization in a political savvy way.

I’d also note that COBOL is only one layer of the stack.

The real complexity lies in also understanding z/OS (mainframe operating systems), CICS, JCL, and the rest of the mainframe runtime, it’s an entirely parallel computing universe compared to the x86 space.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#35

Post by sai18 »

ciaranmca wrote: post #27
sai18 wrote: post #6

Earlier quoted context omitted.

Thank you! The decision makers we work with are typically modernization leaders and mainframe owners — usually director or VP level and above. There are a few major tailwinds helping us get into these enterprises: 1. The SMEs who understand these systems are retiring, so every year that passes makes the systems more opaque. 2. There’s intense top-down pressure across Fortune 500s to adopt AI initiatives. 3. Many of t…

In terms of training your own models, is there enough COBOL available for training or are you going to have to convince your customers to let you train on their data (do you think banks would push back against that?)

There isn’t enough COBOL data available to reach human-level performance yet.

That’s exactly the opportunity we have in front us to make it possible through our own frontier models and infra.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#36

Post by sai18 »

cess11 wrote: post #15

All I can think about when reading this presentation is that Glamorous Toolkit pretty much has this and more.

Reminds me of this comment on the Dropbox HN launch thread: https://news.ycombinator.com/item?id=9224

There are may be other general-purpose tools out there that overlap in some ways, but our focus is on vertically specializing in the mainframe ecosystem and building AI-native tooling specifically for the problems in this space.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#37

Post by sai18 »

tapland wrote: post #24
29athrowaway wrote: post #20

There is a large graveyard of people trying to escape the mainframe, replace COBOL, etc.

I’ve seen a few, 9 figure projects to replace essentially 6 devs and three sysadmins. Another proposed replacement about to fail now, after half the COBOL devs were laid off. So if anyone needs a remote openvms/hp nonstop or junior z/os dev :D

Curious why the COBOL devs were laid off if they're in the middle of a modernization or some sort of replacement project?

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#38

Post by sai18 »

29athrowaway wrote: post #20

There is a large graveyard of people trying to escape the mainframe, replace COBOL, etc.

Absolutely true, and the challenge is that a large portion of modernization projects fail (around 70%).

The main reasons are the loss of institutional knowledge, the difficulty of untangling 20–30-year-old code that few understand, and, most importantly, ensuring the new system is a true 1:1 functional replica of the original via testing.

Modernization is an incredibly expensive process involving numerous SMEs, moving parts, and massive budgets. Leveraging AI creates an opportunity to make this process far more efficient and successful overall.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#39

Post by fock »

gregsadetsky wrote: post #13

I submitted this [0] story a few weeks ago, which led to some discussion and then being flagged since (I think) people were unsure of how verifiable the stats around COBOL were (the submitted page had more than a tinge of self-promotional language). I was curious to ask you, as domain experts, if you could talk more to the "70% of the Fortune 500 still run on mainframes" stat you mentioned. Where do these numbers com…

I work at a shop (a specialized provider for finance in your eyes) which still has the "transaction" workload on IBM z/OS (IMS/DB2). The parts we manage (in Openshift) interface with that (as well as other systems) and I have heard of people/seen the commits moving PL/I to Cobol. In 2021. Given Cobol's nature, those apps have more than 1k LoC easily.

We also sublease our mainframes to at least 3 other ventures; one of which is very outspoken they have left the mainframe behind. I guess that's true if you view outsourcing as (literally) leaving it behind with the competitor of your new system... It seems to be the same for most banks, none of which are having mainframes anymore publicly, but for weird reasons they still hire people for it offshore.

Given that our (and IBM's!) services are not cheap I think either a) our customers are horribly dysfunctional in anything but earning money slow and steady (...) and b) they actually might depend on those mainframe jobs. So if you are IBM or a startup adding AI to IBM I guess the numbers might add up to the claims.

Re: Launch HN: Hypercubic (YC F25) – AI for COBOL and Mainframes

#40

Post by fock »

jclay wrote: post #2

Exciting work! I’ve often wondered if an LLM with the right harness could restore and optimize an aging C/C++ codebase. It would be quite compelling to get an old game engine running again on a modern system. I would expect most of these systems come with very carefully guarded access controls. It also strikes me as a uniquely difficult challenge to track down the decision maker who is willing to take the risk on rev…

> It also strikes me as a uniquely difficult challenge to track down the decision maker who is willing to take the risk on revamping these systems (AI or not).

here that person is a manager which got demoted from ~500 reports to ~40 and then convinced his new boss that it's good to reuse his team for his personal AI strategy which will make him great again.

Post reply on HN