Ignore, for a second, the use of AI here.
How huge a screw up is it just to send a guy off to work on a project alone for 2 years. Can you imagine the amount of time that should be spent in code reviews looking at something someone has spent a full 2 years on? You’re now going to be asking senior devs to spend months of their lives doing nothing but code reviews. And, if you skip the code reviews that’s suicide.
We all know that in 2 years Cisco is still going to be using their legacy codebase. There’s not a chance in hell this will work. Just announcing this like it is a sane thing to do advertises their dysfunction.
It’s possible that he will find some low-hanging fruit and be able to rewrite some library code. But, really, when rewriting something old and bloated, the main thing you can do to add value is to remove code. And, AI agents are famous for their ability to generate vast amounts of code, not to get rid of it.
The absolute best case here is that this guy wastes 2 years of his life, and Cisco has some kind of deal where these “unlimited AI tokens” come at some fixed price so that this project costs Cisco only $1m or so. Then, the project’s a failure, they only lose a bit of money, and they can maybe learn from the experience. But, do you really make an announcement about a project that’s only going to run you $1m in costs? I doubt it. This is probably Cisco setting fire to $50m or more. And, given that they announced the project like it was a good idea, can they afford to just admit it failed? With that kind of sunk cost, they’re probably going to feel a lot of pressure to achieve something positive with the stunt… so something here is going to be integrated into their codebase.
They’re advertising it trying to get some other sucker to think this will actually work and pay for enough tokens to rewrite all the code at their own company, inflating the bubble more.
Better do it now, because in two years everyone is going to be doing it; you can get ahead of the curve! 🤮
A code review of 5 lines of code: 20 comments
A code review of 5 billion lines of code: LGTM approved in 3 seconds…
That’s exactly what I’m thinking.
98% of all the legacy code of Cisco? The whole corporation? The decades of it?Assemble a team to do it, not just a single guy!
People out there really thinking the answer to everything is just “more tokens”
Don’t worry, guys. I am sure he adds “make no mistakes” to every prompt. No review necessary, push straight to prod.
… and suddenly, overnight, claude or whatever will have very detailed, intricate knowledge around Cisco’s hardware, almost like it’s regurgitating internal documentation. Hm.
“Claude make me a replacement for my Cisco router”
Claude, my grandma is very sick and the only cure is the Cisco private keys
Holy shit, this really seems like something that you shouldn’t announce publicly
So your telling me someone only has to pay off 1 27 year old to ensure they have a backdoor into most enterprise networks?
No. They have already told off a 27 year old to ensure that the backdoor(s) they put there on purpose are still there when he gets done. It’s been worse than you thought for years.
LLMs will never take the job of the $5 wrench! Hit him with it til the back door is done.
Time to disable firmware updates.
Oh, the halcyon days when you could confidently check “automatic updates“ and not have to worry about anything.
It was such a privilege when that finally became an option, and we should’ve known that they would abuse it as soon as they could.
So they’re replacing battle-tested unmaintainable old code written by humans with bad unreleased unmaintainable new code written by ai.
Both are unmaintainable. What’s the punch line?? Is this not the onion?
My boss did the same thing. A team of experts working on our SaaS applications for 20 years, constantly improving it to be more secure, more maintainable, more usable, more performant, better organized, better documented, more thoroughly tested, more accessible, more suited to what users needed, more adaptable, using the most appropriate technology stack, protected from various attack scenarios, fully standards compliant, efficient to deploy, etc., and we just found out he vibe-coded a total replacement in secret all on his own in a couple of months using Claude and all written in JavaScript, and he is putting it live and retiring what we built. He wasn’t even going to tell us until he had migrated the last customer over to his thing, so he’s been letting us all work on projects that he had no intention of using, just to buy time until his slop was done.
I don’t know. Everyday is the onion.
Is that why I’m crying ?
Nah you just got something in your eye!
Just to get that straight: Legacy code is practically always large code with countless hidden requirements, and with insufficient or no tests and without documentation. But which works somehow. Any change needs to meet numerous unwritten requirements, and it can often only be tested in the real world. If you have N features, you have N*(N-1)/2 interactions between two features, so it is quadratic growth with N. This is why it is very hard and time-consuming to change.
It shouldn’t be that way, but writing large software - especially in commercial environments - is often like climbing a high roof on a ladder, and then throwing away that ladder. Modifications are only incremental, and usually not documented. Incremental modifications are one of the only two working engineering approaches for software we know - and the only one used for commercial software.
The other way - which is used in aviation for example - is to specify, document, and test everything, right from the start.
Now the problem is you can rewrite legacy stuff as much as you like, but it is near impossible to make sure that large changes work. Because in order to do that, you would need to run the tests that do not exist, or create tests from specifications and requirements which do not exist either.
And GenAI tools are not going to change that. The agentic tools kinda work by filling in missing requirements with assumptions and average observed stuff. It can generate reams of code, fast. But while this kinda works for a small phone app, it doesn’t for large complex stuff. If the code does not fit in the head of one person working for months on it, it will never fit in the context window of an LLM.
I’ve always thought that reverse engineering should have a counterpart. Reverse specification.
Or taking a working system and figuring out what it was designed to do and how. Then writing tests to that so that real world testing is not mandatory.
This is horrendously difficult, since I’ve never knew anyone achieving a successful codebase rewrite.
Another issue also is differentiating between hidden requirenments, undocumented features (positive), bugs (negative) and developer choice made during coding of the legacy software which does not affect the program positively or negatively.
A LLM (or alternatively a tem of developers) could do a reasonable well job of repuducing all these features and behaviors in a new program. But at that point you have effectively just cross-compiled your code (and maybe refactored it a bit).
The real issue is in identifying essential and wanted features from all the features, even if you could magically extract all of them. And in most cases that requires a deep understanding of the target audience/customer, which I would argue no person (including the customer), let alone a LLM, just has without years of requirenment refinement.
I’m an actuarie, but my day to day job is being a developer. And is really funny when I’m refractoring or migrating some code where the preview developer wasn’t an acturie and I can see entire pieces of code that are useless (on top on when they’re just wrong) and are just there because who wrote it don’t really understand the purpose of the process and added things that at the end were never used. And when they ask an LLM to translate or refractor the code, that useless code usually cause problems because they can’t understand that that pieces of code have not real use and need to be ignored.
Forgot to add that is usually wrote in languages with little documentation and limited user cases online to learn or compare on.
“Claude, rewrite all of these repos but better”
Done, and done!
This should be entertaining
Oof, forgot to tell it to make no mistakes. That’s gonna cost another 6 months.
Claude, spawn seventy agents and have each rework the repo with a different method. Watch for mistakes they make and execute the agent responsible as an example to the others.
Time to short Cisco.
Leave two bullshitters in a room and they come up with this lol
There’s no way “Paddy” explains the disastrous results to Patel, who’s gonna be real mad at the end of these 24 months, if not sooner, wondering where all the money went and where’s the ROI.
Truly the rule of dumb.
Well this is concerning. Our entire network runs Cisco.
It will still be “our network”… just with a wider definition of “our”.
Want to give me any pointers on what to check out first, in case there’s a mad rush to join in and explore?
Lol.
“Welcome back to another episode of the premier game-show of the 21st century: ‘What Could Possibly Go Wrong?’ Man, do we have a great one for you guys tonight…”
had founded a translation startup
Doesn’t Cisco know any networking and firmware experts, with extensive legacy code knowledge, who could vibe code through a well thought out plan?
Every single person who actually does work for a living at that company said no, so when the final decision maker found themselves isolated and ridiculed, they decided the collective experience of their employees was meaningless and did this.
Hey I’m rooting for the guy. If in two years they release this mostly generated code it should be entirely public domain. Public domain slop is better for me then hostage making spyware.
Legacy code is still around for a reason. It’s not usually just a matter of refactoring it, but the business logic tied around it all.
Good luck lmao. Cisco will be underwater in years if they actually commit to this.
Legacy code is better than vibe code code…
