It doesn't help that the west has a clear bias wherein moving "up" is moving away from the work. Many executives often don't know what good looks like at the detail level, so they can't evaluate AI output quality.
I think another part of it is that AI tools demo really well, easily hiding how imperfect and limited they are when people see a contrived or cherry-picked example. Not a lot of people have a good intuition for this yet. Many people understand "a functional prototype is not a production app" but far fewer people understand "an AI that can be demonstrated to write functional code is not a software engineer" because this reality is rapidly evolving. In that rapidly evolving reality, people are seeing a lot of conflicting information, especially if you consider that a lot of that information is motivated (eg, "ai is bad because it's bad to fire engineers" which, frankly, will not be compelling to some executives out there). Whatever the new reality is going to be, we're not going to find out one step at a time. A lot of lessons are going to be learned the hard way.
Yes, and they work really well for small side projects that an exec probably used to try out the LLM.
But writing code in one clean discrete repo is (esp. at a large org) only a part of shipping something.
Over time, I think tooling will get better at the pieces surrounding writing the code though. But the human coordination / dependency pieces are still tricky to automate.
I'm (mildly) excited by LLMs because I love a new shiny tool that does appear to have quite some utility.
My analogy these days is a screwdriver. Let's ignore screw development for now.
The first screwdrivers, which we still use, are slotted and have a habit of slipping sideways and jumping (camming out). That's err before LLMs ... something ... something.
Fast forward and we have Philips and Pozi and electric drivers. Yes there were ratchet jobs, and I still have one but the cordless electric drilldriver is nearly as magical as the Dr Who sonic effort! That's your modern LLM that is.
Now a modern drilldriver can wrench your wrist if you are not careful and brace properly. A modern LLM will hallucinate like a nineties raver on ecstasy but if you listen carefully and phrase your prompts carefully and ignore the chomping teeth and keep them hydrated, you may get something remarkable out of the creature 8)
Now I only use Chat at the totally free level but I do run several on-prem models using ollama and llama.cpp (all compiled from source ... obviously).
I love a chat with the snappily named "Qwen3.5-35B-A3B-UD-Q4_K_XL" but I'm well aware that it is like an old school Black and Decker off of the noughties and not like my modern De Walt wrist knackerers. I've still managed to get it to assist me to getting PowerDNS running with DNSSEC and LUA and configuring LACP and port channel/trunking and that on several switch brands.
You?
Like what - the world's most advanced blowjob?
I really think a lot of folks were conned by a smooth operator and a polished demo, so now everyone has to suffer though having this nebulous thing rammed down our throats regardless of its real utility because people with higher pay grades believe it has utility.
It feels like a lot of “AI is inevitable; you are failing to make this abundant future inevitable by your skepticism.”
> But we're the accounting team?
> Doesn't matter. This is a SD-Native company now. We believe everyone can be more productive with an SD-based workflow.
For the record all your prompts are tracked and easily viewable by whoever oversees it at your company. Don't prompt more than you have to and certainly don't give it your best ids. This is value at scale.
Yes, we have craftsmanship, but at the end of the day everything is ephemeral and impermanent and the world continues on without remembering us.
I think both the IC and executive are correct in superposition.