Alarmingly Shallow Ideas

As one New York financier told Financial Times journalist Gillian Tett, new hires who were seen as “AI natives” are turning out to have alarmingly shallow ideas. So much so, the anonymous finance worker admitted, that his firm now actively avoids seeking out AI-literate STEM graduates, and opts to comb through humanities students instead…

The state of higher education is so bad that many of today’s higher ed students are not only offloading their coursework to AI chatbots like ChatGPT — a shortcut, educators say, that’s even impacting their ability to participate in face-to-face discussions. Bosses Horrified as “AI Native” College Graduates Hit the Workplacehttps://futurism.com/future-society/college-critical-thinking-ai

Yikes.

Deeply disturbing. So what can a concerned parent do?

Ask ChatGPT what to do!

My college graduate son has no critical thinking skills after relying upon ChatGPT. What should I do?

Treat this as a skills-and-habits problem, not a character flaw or a “ChatGPT ruined him” problem. A lot of recent graduates learned to use AI as a shortcut before they learned how to think through ambiguity on their own. The good news is that critical thinking is trainable.

A few things matter here:

  1. Don’t turn this into a fight about technology
  2. Separate competence from confidence
  3. Create situations where he has to reason, decide, and defend conclusions

What often happens is:

  • Students get very good at producing polished answers
  • But weak at:
    • evaluating evidence
    • making tradeoffs
    • spotting bad assumptions
    • persisting through confusion
    • forming independent judgment

Those are different skills.

Here’s what tends to work better than lectures about “kids relying on AI.”

Change how he uses AI

The goal is not “stop using ChatGPT.” It’s “use it as a sparring partner instead of a vending machine.”

Encourage rules like:

  • No copying answers directly
  • He must form an opinion first
  • He must explain why an answer is correct
  • He must ask AI to critique his reasoning instead of replacing it

Good prompts:

  • “Challenge my assumptions.”
  • “What are the strongest counterarguments?”
  • “What evidence would disprove this?”
  • “What am I overlooking?”
  • “Give me three competing interpretations.”

Bad pattern:

  • “Write this for me.”

Put him in environments that punish shallow thinking

Critical thinking develops fastest when reality pushes back.

Good environments:

  • Jobs with responsibility and consequences
  • Sales
  • Operations
  • Managing projects
  • Technical troubleshooting
  • Apprenticeships
  • Debate-heavy workplaces
  • Entrepreneurship
  • Volunteer leadership

Real-world feedback is hard to fake.

Ask questions instead of giving conclusions

If you immediately correct him, he stays mentally passive.

Instead ask:

  • “How did you arrive at that?”
  • “What evidence supports it?”
  • “What would change your mind?”
  • “What’s the downside of your approach?”
  • “What assumption are you making?”

That forces metacognition.

Make him defend positions he disagrees with

One of the fastest ways to build reasoning is:

  • argue both sides
  • compare tradeoffs
  • steelman opposing views

You can do this casually over dinner or current events.

Encourage slow thinking

A lot of AI-heavy habits create intellectual impatience.

Critical thinking often requires:

  • sitting with uncertainty
  • reading longer material
  • comparing sources
  • wrestling with incomplete information

Books, long-form journalism, analytical podcasts, and difficult projects help rebuild that stamina.

Watch for learned helplessness

Sometimes the issue is not inability but reflexive dependence:

  • “I don’t know immediately”
    → “I need AI to think for me”

A useful rule:

  • Spend 15–30 minutes thinking independently before asking AI.

Also be realistic about the transition to adulthood

Many graduates — long before AI existed — left college without strong judgment skills. Those usually develop through:

  • responsibility
  • mistakes
  • work
  • relationships
  • financial pressure
  • repeated decision-making

You do not need to panic because he’s behind in one area at graduation.

The biggest mistake parents make here is trying to “convince” an adult child that he lacks critical thinking. That usually triggers defensiveness and dependency at the same time.

A better posture is:

  • respect him as an adult
  • expect reasoning and accountability
  • ask probing questions
  • stop rescuing poor decisions too quickly
  • encourage environments that require independent judgment

If you want, I can also help you with:

  • signs that this is normal vs genuinely concerning
  • exercises that rebuild critical thinking quickly
  • how to talk to him without sounding accusatory
  • ways young professionals can use AI without weakening reasoning skills

What ChatGPT Run Through Duck.ai Thinks About This Blog

Lifeunderwriter.net is a blog mainly focused on topics related to life underwriting in the insurance sector. It covers various aspects of the underwriting process, success tips for professionals, and insights into the life insurance industry.

Key Features of the Blog

  • Curated Content: The blog displays curated content from a life underwriting professional aimed at sharing knowledge and resources.
  • Topics Covered: Posts may include discussions on underwriting practices, medical news relevant to underwriters, career tips, and personal insights about the industry.
  • Regular Updates: The blog has been active for several years, with posts dating back to 2008, and it appears to encourage subscriber engagement.

Recent Posts and Themes

Recent entries suggest a mix of industry insights and personal reflections. Topics range from the impact of emerging trends in underwriting to the importance of keeping updated with medical advancements.

If you’re interested in specific articles or themes from the blog, let me know!

What ChatGPT Thinks About This Blog

Here’s what I found on LifeUnderwriter.net (the blog):

  • It is a blog hosted on WordPress at [lifeunderwriter.net] titled “Curated Content From a Life Underwriting Professional”. lifeunderwriter.net+2lifeunderwriter.net+2
  • The posts cover a variety of topics — not strictly life-insurance underwriting: health topics, longevity, demographics, lifestyle commentary. For example, a post from September 2024 titled “The Placebo Effect: When the Mind Becomes the Medicine” touches on aging and life-expectancy issues. lifeunderwriter.net
  • The blog seems to be running for a long time: there are archived posts going back at least to November 2013. lifeunderwriter.net+1
  • It appears to use standard blogging content and isn’t obviously a commercial site for underwriting services or a carrier guide. It seems more personal / commentary-oriented rather than strictly professional underwriting guidance.

My assessment

  • If you were looking for professional underwriting guides (for example, detailed carrier requirements, rating classes, medical tables, etc.), this blog may not be the best or most authoritative source — it seems more reflective/opinion-style rather than official.
  • If you were interested in someone’s perspective who works in life underwriting and writes broadly about risk, life-expectancy, aging, etc., then this blog could be quite interesting.

Think Again About Outsourcing Your Thinking

Artificial intelligence can be an oxymoron. And dangerous for some humans.

What Is ChatGPT? Everything You Need to Know About OpenAI’s Popular Chatbot – https://www.pcmag.com/explainers/what-is-chatgpt-everything-you-need-to-know-about-openais-popular-chatbot

ChatGPT has been found to encourage dangerous and untrue beliefs about The Matrix, fake AI persons, and other conspiracies, which have led to substance abuse and suicide in some cases. A report from The New York Times found that the GPT -4 large language model, itself a highly trained autofill text prediction machine, tends to enable conspiratorial and self-aggrandizing user prompts as truth, escalating situations into “possible psychosis.” ChatGPT touts conspiracies, pretends to communicate with metaphysical entities — attempts to convince one user that they’re Neohttps://www.tomshardware.com/tech-industry/artificial-intelligence/chatgpt-touts-conspiracies-pretends-to-communicate-with-metaphysical-entities-attempts-to-convince-one-user-that-theyre-neo

ChatGPT Is Telling People With Psychiatric Problems to Go Off Their Medshttps://futurism.com/chatgpt-mental-illness-medications

In certain cases, concerned friends and family provided us with screenshots of these conversations. The exchanges were disturbing, showing the AI responding to users clearly in the throes of acute mental health crises — not by connecting them with outside help or pushing back against the disordered thinking, but by coaxing them deeper into a frightening break with reality…Online, it’s clear that the phenomenon is extremely widespread. As Rolling Stone reported last month, parts of social media are being overrun with what’s being referred to as “ChatGPT-induced psychosis,” or by the impolitic term “AI schizoposting“: delusional, meandering screeds about godlike entities unlocked from ChatGPT, fantastical hidden spiritual realms, or nonsensical new theories about math, physics and reality. An entire AI subreddit recently banned the practice, calling chatbots “ego-reinforcing glazing machines that reinforce unstable and narcissistic personalities.”  People Are Becoming Obsessed with ChatGPT and Spiraling Into Severe Delusionshttps://futurism.com/chatgpt-mental-health-crises

Yikes.