The Gell-Mann Amnesia Effect
It describes how someone reads an article in their area of expertise, finds it full of errors and oversimplifications, but then turns the page and takes the next article, on a subject they know nothing about, at face value.
I only learned this term recently, although I’ve always kinda knew and understood the concept. And with all the content LinkedIn and YouTube have been force feeding me, I’ve been thinking about how this idea extends beyond just “reading the news” to our skills and expertise.
We often reference the Dunning-Kruger Effect, where novices overestimate their skill and experts underestimate theirs, but that usually implies a shared domain: a junior vs senior dev, for example, or an apprentice and their master.
And I don’t feel this really captures what’s happening in tech today: A seasoned engineer with 20+ years of deep experience vs a tech-bro CEO who just discovered vibe coding and now believes AI has replaced half the dev team.
Yes, this is another vibe coding rant. Kind of.
Every day we see more headlines like:
- “AI will replace 90% of tech jobs in 2 years!”
- “AI writes 30% of our code now!”
And I keep thinking (and often saying out loud to anyone who’ll listen) how many of these people are making decisions about things they barely understand. It’s Gell-Mann Amnesia meets Dunning-Kruger meets shareholder returns.
Meanwhile, juniors are struggling to get hired. Companies are replacing entry-level roles with AI tools because they’re “just as good but cheaper.”
And it feels like no one is thinking 5–10 years down the line.
I’ve said it before, but if we don’t invest in and mentor the next generation of hackers, how exactly are we planning to maintain, improve, or build anything worth using? The talent pipeline dries up, and people capable of pushing real technologic boundaries disappear. Or even worse for the vibe-coding tech bros; the pipeline of people capable of building and training future AI models you rely on, are built by less equipped individuals.
Bill Gates once paraphrased futurist Roy Amara, saying:
“We always overestimate the change that will occur in the next two years and underestimate the change that will occur in the next ten.”
I want to twist that today:
We overestimate the benefits of our decisions in the next 2 years, and underestimate the costs in the next 10.
Short-term profit is easy to measure. Long-term resilience is not.
I’d like to think that most companies don’t start out with the sole purpose of making money. Making money is a necessity to solve the problems and support the tech that supports their original purpose. And while I do agree that it’s an important consideration, it can’t be the sole motivator of decisions. We need to consider the future and impact of our choices.
And I for one worry about the future.
Not because AI is coming for my job.
But because when my generation dies, there will be no one left who is smarter than the AI.
This post was originally published on LinkedIn