Rendered at 19:44:14 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Taikonerd 5 hours ago [-]
Does this one engineer have the domain knowledge to know WHY the old code was written the way it was, and what the graybeards would have done differently if they could start again now?
Otherwise he's just going to replicate all the legacy bugs and questionable design decisions.
classified 5 hours ago [-]
I have no doubts that there will also be new bugs.
koskokos 4 hours ago [-]
the premise does sound a lot like written by someone who is looking for hype and not sounding credible
sleepyguy 4 hours ago [-]
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?
oblio 4 hours ago [-]
The entire story sounds very weird.
Refreeze5224 5 hours ago [-]
As much as I dislike AI, having worked on Cisco gear for years, I can't imagine AI can put out a worse product. If the re-write is full of bugs and security holes and static SSH keys, then it has not changed at all.
Aperocky 4 hours ago [-]
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.
icedchai 4 hours ago [-]
It's sad to hear how Cisco has fallen. I remember working on some early ISP networks in the 90's. Cisco was everywhere!
benjojo12 4 hours ago [-]
Just because something is/was widely deployed does not mean it was good
icedchai 4 hours ago [-]
True. There were few (no other?) options for routers back then. I have fond memories of locking myself out of an ISP's core router then having to power cycle it.
runjake 2 hours ago [-]
It doesn't, but Cisco was great and they've just evolved into a laughing stock. Their stuff is really bad these days.
And they've overstretched their product line to too many things, trying to be the "be all" company. Fortinet is making the same mistake, but they're earlier in that process.
I mean, it's not really a mistake on their parts, their primary goal is to get rich and they are succeeding.
Citation: I've been working with Cisco technologies since the mid-1990s. At my current job, we are a few weeks away from phasing out the last of our Cisco junk. And since people will ask: to Juniper/Mist and Arista.
kotaKat 2 hours ago [-]
They didn't even need the AI to make thousands of hot bricks nationwide. Here's just one of the latest hits...
"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 :)
Aperocky 4 hours ago [-]
Unless they also have 750K tests like sqlite do, I can't imagine this will go well, even if/especially if the legacy code warrants a refactor.
williadc 5 hours ago [-]
There's no goal mentioned in this article as why 98% of the code needs rewriting.
HarHarVeryFunny 5 hours ago [-]
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?
vonneumannstan 4 hours ago [-]
Somebody needs a promo packet. Duh
add-sub-mul-div 5 hours ago [-]
AI has electrolytes!
classified 5 hours ago [-]
The hardware it runs on has capacitors as its components and some of them do in fact contain electrolytes.
analognoise 4 hours ago [-]
It’s what the shareholders crave!
yako21000 4 hours ago [-]
They also seem to crave everything that has the word AI in it.
piker 5 hours ago [-]
Is this like a PR piece for the guy? It's odd to see him singled out in a piece that would be normally be about the company, the CEO or the decision itself.
m4rtink 4 hours ago [-]
Seems like preparing who to blame if/once the effort fails. ;-)
koskokos 4 hours ago [-]
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.
alwa 5 hours ago [-]
Rewrite it in service of… what exactly?
rustyhancock 5 hours ago [-]
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.
rafram 5 hours ago [-]
If nobody knows how the old code works, how will anyone know how the new code (written by an autonomous agent) works?
rustyhancock 5 hours ago [-]
Regression tests?
I think people are assuming the worst but AIs most helpful contribution beyond churning out code is explaining the code base.
Who knows if they will do a good or bad job that's down to the engineers and not the tools imo.
paimapi 3 hours ago [-]
I think this is actually the opposite in practice. LLMs generate better tests than they are at assessing which tests are effective (and, inferentially, how a system should behave). See: https://arxiv.org/abs/2410.21136
Why is that better than having the agent(s) write regression tests or explanations of the old codebase?
5 hours ago [-]
LoganDark 4 hours ago [-]
I don't think no one knows how it works. I just think the people using the word "legacy" for it are boneheaded.
mr_roboto 4 hours ago [-]
He'll pull it off, get feature complete, and spend a year or two with better models as they are released ironing it out. We just did an experiment, in four weeks generated 3500 commits, 200k sloc with a 1:1.15 ratio of production to test code and it all works very well. We are well on our way from 10x to 100x.
Ancalagon 3 hours ago [-]
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.
mr_roboto 2 hours ago [-]
It is for internal use and so far so good. We are finding bugs and we just point the models at it with a strict red-first TDD approach and they've done very well fixing them. It certainly isn't perfect but the issues are very similar to what you get with a team of humans doing the same thing.
The main takeaway though is we had one person, in a single month, do the equivalent of at least a couple years of work for a small team. We view bugs and performance issues as a currently inevitable part of the process and we are dealing with them with models just like we do with humans on every other project already. Overall though it is representing an absolutely massive speedup. If you work in an environment where the models make egregiously more mistakes than your human counterparts then I am quite jealous.
emoII 4 hours ago [-]
Well they say the last 20% of the work takes 80% of the time so if he gets the prototype in 4 weeks, which I have no doubt he will be able to do, and assuming that prototype is the first 80% of work, then he should be able to do this in 20 weeks. He even has some margin! Looking forward to seeing the results
dmortin 5 hours ago [-]
Misleading title, someone should fix it. 98% of legacy code. Check out the full title of the article.
loloquwowndueo 4 hours ago [-]
Does Cisco have non-legacy code?
hangrybear666 4 hours ago [-]
My favorite description of JAVA is that it's a language where you are deploying instant legacy code.
m4rtink 4 hours ago [-]
I guess Cisco decided it has not alienated its customers enough till now & its finally time to get people running for the woods - at least if those peoples would like their network to continue working.
balderdash 4 hours ago [-]
We have an embedded system in one of product offerings that was largely developed using a bunch of “antiquated” technologies (over the past twenty years) and over the past year the two software devs that maintained it have retired. This normally would have big problem, but the entire codebase was re-written, documented, and modernized in a matter of about 3 months (for about $20k in tokens, and a mid level developer spending 50% of their time on it over that period). So it doesn’t surprise me to think a company like Cisco has piles of situations like this.
petra 4 hours ago [-]
That's really interesting.
What have been achieved using this port?
And how did you make sure the port is correct?
petra 4 hours ago [-]
I think Cisco is an interesting use case for AI, because it's code, probably:
-Works according to a defined specification
-Within the bounds of that specification, has a lot of code written to optimize speed, cost, latency, etc - all measureable goals
-Written in c, with all it's weakness
-Given limitless engineering work, some could be ported to better hardware
-the new system could be automatically compared to the old system for functional correctness
All those factors fit well with agent based development.
Btw, many of them are true in general to embedded systems.
mkjs 4 hours ago [-]
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.
petra 4 hours ago [-]
That's a good point.
I wonder whether AI is any good at looking at that code,running the system, and documenting those edge cases?
mkjs 3 hours ago [-]
I'm probably not describing the scale of the issue adequately. Lots of these bugs only show up when you have a specific bit of hardware on a specific version of code, and it's connected to another specific bit of hardware running another specific version of code.
Lots of this stuff should work in theory, you only find out that it doesn't in practice when you try it on real hardware. And there are thousands of bits of hardware.
wil421 4 hours ago [-]
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.
Cyph0n 4 hours ago [-]
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.
pphysch 4 hours ago [-]
The first and last bullets are extremely optimistic. How do you possibly simulate all the weird interdependent behavior in real world networks?
petra 4 hours ago [-]
Given that a Cisco switch can be replaced with some other company's switch(at least in theory, idk), without weird unknown cases interfering, why would this be a problem ?
Cyph0n 4 hours ago [-]
Not that straightforward. Similar to CPUs and other HW, there are errata and interop quirks between devices.
There are also tight time budgets (basically SLAs) that must be met along with memory considerations (both in SW and on the NPU/HBM), not to mention how the device needs to respond to load and various failure scenarios.
Taikonerd 4 hours ago [-]
There also seems to be some weird hero-worship from the CEO, directed at this 27-YO engineer? Like, "he is the one who can save us."
cheevly 3 hours ago [-]
Shocking to realize how many on HN do not realize that this is NOT a tall order, and has not been a feat for at least six months.
1970-01-01 4 hours ago [-]
Cisco that powers more than half of the backbone of all things online? Are we trying to lose control of AGI as soon as it emerges??
masfuerte 4 hours ago [-]
When this rewrite breaks the internet AGI won't be able to take over. It's very forward-thinking.
bluegatty 4 hours ago [-]
ha ha .. that sounds like an Onion article. To be fair - if they did a narrow refactor to focus on fixing only obvious and known issues, they probably might be able to pull it off because a ton of that code is hairballs.
> “I’ve given him unlimited tokens because he’s going to refactor code,” Patel told Fortune at a small roundtable dinner. “So I’m like, you can go, you can go nuts.”
I think that Fortune story is better than the Tom's Hardware one. It ties the Cisco anecdote into a larger trend of some people deliberately hiring younger, less experienced developers for their AI projects - because they are more likely to be "AI native".
rasz 4 hours ago [-]
more like AI naive
simonw 3 hours ago [-]
Sadly, I think the label "AI naïve" is better applied to the many experienced professionals who refuse to engage with AI systems as a matter of principle - or who tried out ChatGPT in 2024, saw it make howlingly obvious errors, and wrote off the entire category.
I frequently find myself in conversations with people who are resistant to AI and turn out to have a very skewed idea of what it can and cannot do.
raincom 4 hours ago [-]
'98% of the company's legacy code' is very vague. How many code bases? How each code base is connected to any supported Cisco product? How many KLOC the company's legacy code?
blobbers 4 hours ago [-]
I mean, this is going to be easy. I've worked on Cisco gear before and this will be a simple job for AI. The big question is what the goal is... so you've rewritten new C++ code or ported to a newer version of Linux? Or you've unified the codebase of the Catalyst + Meraki switches?
Not clear to me what he's doing. Re-implement switching? Simplify features? Reduce LoC? Add test coverage? Either way, AI in that world will be helpful. I'm sure it'll spot all kinds of problems in opaque drivers that are hard to follow from MF specs.
classified 5 hours ago [-]
So there's a real risk that Cisco might become history in just a few years. Taking that kind of risk with a rather unproven technology has to be psychosis. Or is that kind of belief a form of Religion?
Maybe Stanford found some more of their stolen code being used by Cisco. /s Cisco origins is a fascinating subject.
insane_dreamer 4 hours ago [-]
rewriting code is the easy part
it's the testing in real world usage to shake out all the edge cases and bugs that's hard and that you can't just write unit tests for
pupppet 4 hours ago [-]
[dead]
causal 4 hours ago [-]
I suspect we are approaching a world where this makes sense to do annually. Opus 5.5 is good enough to improve on most codebases, and Opus 7 will no doubt be good enough to improve on that.
Otherwise he's just going to replicate all the legacy bugs and questionable design decisions.
And they've overstretched their product line to too many things, trying to be the "be all" company. Fortinet is making the same mistake, but they're earlier in that process.
I mean, it's not really a mistake on their parts, their primary goal is to get rich and they are succeeding.
Citation: I've been working with Cisco technologies since the mid-1990s. At my current job, we are a few weeks away from phasing out the last of our Cisco junk. And since people will ask: to Juniper/Mist and Arista.
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 :)
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?
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.
I think people are assuming the worst but AIs most helpful contribution beyond churning out code is explaining the code base.
Who knows if they will do a good or bad job that's down to the engineers and not the tools imo.
That said, there's also research pointing to LLMs encoding existing bugs as test requirements: https://arxiv.org/abs/2607.05139
That CS PHD researcher, Konstantinou, in particular, has written a lot on this: https://arxiv.org/search/cs?searchtype=author&query=Konstant...
The main takeaway though is we had one person, in a single month, do the equivalent of at least a couple years of work for a small team. We view bugs and performance issues as a currently inevitable part of the process and we are dealing with them with models just like we do with humans on every other project already. Overall though it is representing an absolutely massive speedup. If you work in an environment where the models make egregiously more mistakes than your human counterparts then I am quite jealous.
What have been achieved using this port?
And how did you make sure the port is correct?
-Works according to a defined specification
-Within the bounds of that specification, has a lot of code written to optimize speed, cost, latency, etc - all measureable goals
-Written in c, with all it's weakness
-Given limitless engineering work, some could be ported to better hardware
-the new system could be automatically compared to the old system for functional correctness
All those factors fit well with agent based development.
Btw, many of them are true in general to embedded systems.
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.
I wonder whether AI is any good at looking at that code,running the system, and documenting those edge cases?
Lots of this stuff should work in theory, you only find out that it doesn't in practice when you try it on real hardware. And there are thousands of bits of hardware.
This whole thing sounds like a deluded vanity project birthed in an ivory tower.
There are also tight time budgets (basically SLAs) that must be met along with memory considerations (both in SW and on the NPU/HBM), not to mention how the device needs to respond to load and various failure scenarios.
Fortune's source was the CEO himself:
> “I’ve given him unlimited tokens because he’s going to refactor code,” Patel told Fortune at a small roundtable dinner. “So I’m like, you can go, you can go nuts.”
I think that Fortune story is better than the Tom's Hardware one. It ties the Cisco anecdote into a larger trend of some people deliberately hiring younger, less experienced developers for their AI projects - because they are more likely to be "AI native".
I frequently find myself in conversations with people who are resistant to AI and turn out to have a very skewed idea of what it can and cannot do.
Not clear to me what he's doing. Re-implement switching? Simplify features? Reduce LoC? Add test coverage? Either way, AI in that world will be helpful. I'm sure it'll spot all kinds of problems in opaque drivers that are hard to follow from MF specs.
it's the testing in real world usage to shake out all the edge cases and bugs that's hard and that you can't just write unit tests for