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.
He doesnt need that when he has Ponytail https://github.com/DietrichGebert/ponytail
Right? ...
I've never heard of Ponytail before, I've read the entire README and glanced through this repo and I'm left so confused. From what I can gather this project is essentially a single markdown file with a prompt that verbosely says "write the simplest code". Yet the repo itself looks so bloated and complex and has so much activity. This feels like satire similar to fizzbuzz enterprise edition[1] but apparently this is the actual state of our industry?
[1] https://github.com/enterprisequalitycoding/fizzbuzzenterpris...
The date picker example is perhaps the best worst they could have picked.
Anyone who has used the built in date picker knows why everyone rolls their own.
Is this entire repo satire?
It's a bunch of text files in a repo with massive churn (all new version 5!), but somehow even the technical debt 'skill' (i.e. text file) has technical debt itself:
https://github.com/DietrichGebert/ponytail/blob/main/skills/...
> ...every ponytail shortcut is marked with a shortcut: comment ... (older code may say ponytail:).
That’s what I thought. Then a colleague introduced it for real in a code review.
It doesn’t matter if it’s satire. Developers seem to be so vulnerable to all these AI promises of ‘automating’ everything.
BTW it’s terrible. It gave two very hollow suggestions that did not solve the real problem. Hour wasted, angry colleagues, no code change.
The AI craze very much reminds me of the crypto craze a few years ago - lots of people new to the industry jumping on the latest trend and building tooling for something that doesn't need tooling, trying to sell shovels in a gold rush, but just spending years creating a gold-plated shovel which nobody needs instead.
And Web 3, Metaverse, Blockchain, NFT… Only this time it’s kind of useful.
Yes that's true it is more like the dot.com bubble in that regard - a useful technology which will clearly grow over time, but overhyped in the initial phases as everyone tries to be 'AI' in 2026, in 1999 it was online, whether it fits with their business or not.
See also: https://en.wikipedia.org/wiki/Purple_hat_therapy
I have no doubts that there will also be new bugs.
the premise does sound a lot like written by someone who is looking for hype and not sounding credible
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?
His startup was acquired by Cisco so not weird for Cisco's CPO to know the startup's founder/CEO. That said, not sure how knowledge on speech translation means he's totally qualified on rewriting infra/networking/cybersecurity (Cisco's primary fields of operation) code. Unless the legacy code expected to be rewritten is constrained on related services/solutions, e.g. CVP or/and WebEx.
His job isn’t to rewrite all the code. His job is to make the market satisfied that Cisco is “more AI” than competitors.
I sincerely hope this is what is actually happening behind the scenes
The entire story sounds very weird.
They met each other by chance and began work rewriting the entire company's codebase over a firm handshake
You forgot to mention the translation company he helped found was also acquired by this same CEO. :))