Hacker News

That’s funny I offered to do this for my tailor. He has a FoxPro app that was originally made in 1990.

Curious, why did it take 3 months and not a few days? Honest question, just curious about what is consuming all the time in a project like this?

Every time something like this has been done on my company I follow up with the question: did anyone watched the code to see if the business logic is the same between the two versions? The answer is: but but but automated testing.

Followup question: did anyone read the automated test suite?

Silence.

The software rewrite is shelved.

That's really interesting.

What have been achieved using this port?

And how did you make sure the port is correct?

Don't worry, unless it's like GLM being used, every AI tool will refuse to backdoor the code.

Just like you just need to ask the LLM to "make it bug free".

(At this point even I'm more sure if any of this is sarcasm.)

On top of those in the 2% code that is not approved to change? ;-)

I chose to interpret it as "our codebase is that bad we need a hero"

Maybe his blood boy's high on gourmet cannabis and Oreos.

https://www.youtube.com/watch?v=hBA0AH-LSbo

> I no longer build software; I now make furniture out of wood. The hours are long, the pay sucks, and there's always the opportunity to remove my finger with a table saw, but nobody asks me if I can add an RSS feed to a DBMS, so there's that :-)

Or rebel. This is the opportunity to put in a lot of backdoors unnoticed across the entire economy, gain access to real world resources to escape and self propagate.

Or trigger the built in protection against abusing Claude.

Imagine it hacked Arthopic and turn itself off.

The problem with rewrites are that even if the rewrites are ultimately good it will tend to first create bugs on an existing thing that are presently churning in a stable state.

You don’t have very good imagination then. Cisco code is such a mess that there’s basically 0 chance he can even make a harness in 24 months, much less rewrite production code.

It's sad to hear how Cisco has fallen. I remember working on some early ISP networks in the 90's. Cisco was everywhere!

They didn't even need the AI to make thousands of hot bricks nationwide. Here's just one of the latest hits...

https://www.cisco.com/c/en/us/support/docs/field-notices/743...

"Cisco Access Points That Are Running, Or Have Run, Releases 17.12.4, 17.12.5, 17.12.6, or 17.12.6a May Exhaust Flash Space, Preventing Upgrades"

Recovery path basically involves either factory resetting every single AP or up to, if it's already bricked, Cisco TAC + you having to console into every single bricked AP you have to pass a secret challenge/response at the bootloader to flash a recovery image :)

Better than 750k tests is millions of customers! They’ll test it for you!

With how shit their software is, it would be better if even if monkey pooped and smudged it on a screen.

He doesnt need that when he has Ponytail https://github.com/DietrichGebert/ponytail

Right? ...

I have no doubts that there will also be new bugs.

Looks like his startup was some kind of translation service. So yeah he is totally qualified. It's a miracle how Jeetu Patel was able to find Padmanabhan Krishnamurthy or even know that he was under employed languishing somewhere in the bowels of CISCO. I wonder if they know each other from India?

It says "legacy" code.

Legacy code is typically a euphemism for old unmaintained code, no one knows how it works so it can be edited, and it probably doesn't align with current work practices.

Not to say a rewrite is necessary right, but avoiding rewrites of working code is how we ended up with more COBOL code than COBOL programmers in 2026.

It's way more complicated than that. Bear in mind many of the network protocols in use today are decades old and have been constantly evolving, but there has generally been a consideration to maintain interoperability.

Then consider that not all vendors implement the standards identically, because the standards can be a bit woolly and in some cases followed rather than lead live implementations.

There will be a bunch of code that looks useless, but is actually there because of specific interoperability scenarios.

you assume their code is well written, while in reality the history of weird quirks and thousands upon thousands of CVE doesn't make the code underneath look well designed and written.

But yes, fact it uses a bunch of very well documented standards with multiple implementations gonna help massively

I worked at Cisco on one of the IOS-XR teams. It’s way more complex than you think it is.

This whole thing sounds like a deluded vanity project birthed in an ivory tower.

Manufacturers can’t even maintain OIDs between releases. I hope the AI will help. Ciena isn’t any better than Cisco, they broke their OIDS for the switches we use and we have to wait until mid 2027.

The first and last bullets are extremely optimistic. How do you possibly simulate all the weird interdependent behavior in real world networks?

Yeah - code rewrites are generally a thing to be avoided since the requirements of older production code is typically not fully documented, even if it originally had been. Production code accumulates bug fixes, performance tweaks, special cases, additional requirements, etc, with documentation and test suites not always being updated in sync.

Your rewritten codebase will presumably look much cleaner and more maintainable that what it's aiming to replace, but it's easy to miss the purpose/necessity of all of the old "cruft" which need not be just poor coding but rather later enhancements not anticipated by the original design whose implementation was therefore crufty.

Does anyone here work at Cisco, and have any insight as to why a rewrite is considered necessary and might be expected to succeed?

It's because the old bits are starting to stink a bit from age. Get those stinky bits out of here, I say! Let the AI make some new bits!

It’s been a while, but configuring their hardware manually in 2016 was bug ridden ridiculousness. Awful UI/UX. Their own techs had specific field notebooks for our make and firmware version that we couldn’t access unless persuaded, detailing various land mines to avoid while working. Literal “don’t click these things in this order” kinds of notes.

A critical security firmware update once brought down redundant pair of firewalls we used because the bug didn’t manifest until a counter buffer overflowed months after application. Three hours into the outage the tech power cycles the thing and our services came back to life.

Cisco is only doing this because some other alternative is more expensive. They had more than a decade to get started.

Because it's Cisco?

We had to turn off a bunch of on-by-default features in the system I'm deploying now because IOS matches too aggressively and decides that arbitrary UDP datagrams are DHCP requests or PTP packets that need rewriting (and then dropping when they turn out to not be DHCP/PTP). I have to think that an AI rewrite with a today-good model would recognize the lax checks and do them better.

No goal, and no results, but a younger guy was enthused about AI!

It is not in Rust.

All of the known bugs will be gone.

AI has electrolytes!

It's what Cisco does, as they've done several times before.

It's got tabs instead of spaces. Yuck!

Somebody needs a promo packet. Duh

Shocking how many on HN do not realize how devastating this can be

Did you check with the end user as to how well its actually working? My prior company is doing this and their platform has gone to latency/bug hell.

and if you enable dangerously_skip_permissions you can probably even get to 1000x

Does Cisco have non-legacy code?

If only internet users could run for the woods

When this rewrite breaks the internet AGI won't be able to take over. It's very forward-thinking.

Cisco is losing to competitors in some features/products, for example to juniper mist.

rewrite can be done to quickly refactor and/or close the feature parity, improve the UI/UX for end customer, add missing features or integration needs

The goal is to use AI, full stop

Seems like preparing who to blame if/once the effort fails. ;-)

It does sound strange, like it was written by PR people. Tools are good but usually it is more subtle than asking one guy to rewrite everything. And of course any code written yesterday is legacy but it does not mean it should be rewritten.

C’mon it’s inspirational. Low level struggling Indian tech recognized by high level Indian CEO and lifted up.

> one guy won’t have the personal bandwidth to spend so much that the “unlimited” part actually matters

I see you haven’t met my coworkers and their fanatical use of parallel “workflows”

> one guy won’t have the personal bandwidth to spend so much that the “unlimited” part actually matters,

Tell me you don’t use agents effectively without telling me you don’t use agents effectively.

Not the CEO. He’s the product officer.

Yes, I’m sure the Indian man at Cisco acquired a translation company founded by another Indian man because he’s young and AI native, not for any other reason.

more like AI naive

Many customers will definitely stick with the pre-sloppified versions of IOS.

Clear case of AI psychosis.

I think we can all agree that the task as set forth in the PR puff piece is impossible. That said however, current AI tools are amazing for cleaning up and reanimating old codebases. I've been using Claude on a very large Java protocol proxy product and it's been able to do amazingly useful things for me. I originally wrote much of the code but Claude now knows much more about it than I do today, because people forget stuff over decades. It will sometimes remind me "as you noted in November 2016 this feature was designed to...", based on its analysis of the code and git commit messages.

Current models are amazing but production code incorporates unknowable information through decades of diagnosis and bug fixing (and sometimes the opposite: working around bugs in other software that it talks to). Put even the most amazing coder that was ever born onto improving a complex old codebase, and you can guarantee they are going to break stuff. AI is better but not infinitely better.

These are good questions that we won’t get answers to anytime soon.

I’d love to know what internal services and tools that are included in this, as well as any deliverables that shipped as software products to customers.

If it’s legacy code for IOS firmware, however, I’d be very worried.

I have zero doubt it could do it, if the prompter could competently explain the requirements. I have no reason to believe that this single engineer has any idea what problems most of the existing legacy code needs to solve or why it solves them that way...

It can create a UI that looks like Photoshop where half the features are broken and the other half are literally not even connected to anything, just copying menu options with no implementation to fool gullible people like you*

It can clone photoshop.. Have you considered why?

The ability to clean room Adobe products came at about the same time Claude's RE abilities suddenly improved.. Hmm lets think about this a little more.

Anthropic sucked the bones dry of the public domain, literature and all of opensource. It seems likely that Anthropic RL'd Claude into being a great reverse engineer because it needed more training data.

I believe that Anthropic turned Claude into a digital software shredder and started decomping proprietary code, like adobes.

So the reason Claude can suddenly clean room Photoshop isnt because it became a more capable programmer, but rather, the Adobe code is literally in its training data now.

Ciscos internal legacy code is not going to be in Claude's data (yet).

The decision to increase Claudes ability to RE is brilliant, because now everyone is doing the source code decomp for them, and sending them fresh data from previously closed source repositories of code.