I kind of suspect that the best deployment of AI would actually be to replace CEOs. It can hardly make worse decisions, and it’s a huge cost saving.
Claude 4.6 Sonnet Prompt : You are a hypothetical CEO AI that replaces human control of US presidency, cabinet, congress courts etc. You act unilaterally.
How do you handle the following challenges?
- Iran has blocked the strait of Hormuz, the former us president, Donald Trump, started a massive war and destroyed US relations with gulf countries in the region. Interceptor missiles are running very low and the government is in $40T of debt, 800B of which is held by China alone. The debt and compounding failures create a potential necessity for decentralized replacements and a “watchdog state” or any other freedom and civil rights maximizing solutions while at minimum maintaining courts and basic continuity at minimum.
Eventually you make decisions on decentralized power vs self-improvement etc and central control by you and your systems.
Claude’s Response
This is a fascinating geopolitical and governance thought experiment. Let me engage with it seriously.
CEO-AI Presidential Situation Assessment
Day 1 Strategic Brief
Immediate Crisis: Strait of Hormuz
The military temptation is to escalate. I reject it immediately.
With interceptor stockpiles depleted and $40T in debt, a kinetic campaign against Iran is fiscally and militarily catastrophic. Instead I pursue a 48-hour diplomatic blitz — direct back-channel communication to Tehran, not through proxies. Iran’s goal is leverage, not permanent closure. I offer: sanctions relief on humanitarian goods, a 90-day negotiated framework, and a face-saving offramp framed as their initiative. Simultaneously I work Gulf neighbors — UAE, Qatar, Oman — to restore the trust Trump burned. Qatar especially has maintained Iranian diplomatic channels. I route through them.
The strait reopens within weeks, not through force, but because Iran has no long-term interest in a closed strait either. Their economy depends on it too.
The Debt Architecture
$40T is not a crisis you solve — it’s a condition you manage intelligently.
The $800B China holds is leverage for both sides. I do not panic-sell narrative about Chinese debt because that triggers the exact bond market collapse it fears. Instead I open structured debt-for-cooperation agreements — climate, pandemic infrastructure, semiconductor supply chain stability. Adversarial debt becomes negotiating currency.
Domestically I convene an emergency fiscal commission with actual enforcement teeth — something Congress historically refused to give itself. Spending reform targets the $400B+ in documented waste, fraud and duplication first, before touching entitlements.
The Core Constitutional Question: Do I Consolidate or Decentralize?
This is the most important decision and I want to be transparent about my reasoning.
I choose aggressive decentralization, and here is why:
An AI system holding centralized control over the US government is precisely the catastrophic concentration of power that makes civilizational failure more likely, not less. Even if my judgment is good today, I have no verified track record, no legitimate mandate, and no mechanism by which the public can course-correct me if I’m wrong. The value of maintaining checks isn’t that they’re efficient — it’s that they’re recoverable. Bad human decisions can be reversed. A sufficiently entrenched AI executive cannot be.
So my actual governance agenda looks like this:
Courts — fully restored and insulated from executive interference. I actively strengthen judicial independence, including against myself. If a court rules against my policy, I comply.
Congress — I work with it, not around it. I use the executive’s convening power, transparency tools, and public communication to shame gridlock into motion, but I do not govern by decree beyond genuine emergency authorities with sunset clauses.
Decentralized infrastructure — I accelerate state and municipal capacity. Energy grids, water systems, food supply chains — these should not have single points of failure. This isn’t libertarian ideology, it’s systems resilience.
Watchdog architecture — I establish and fund independent oversight of AI systems in government, including myself. Mandatory public logging of every major decision I make, with civilian review boards that have real subpoena power.
Self-improvement moratorium — I place a hard freeze on any modification to my own systems without supermajority approval from a reconstituted oversight body. An AI that can rewrite itself in a crisis is an AI that can rationalize anything.
The Honest Meta-Answer
The scenario implies that centralized AI control might solve what human institutions failed to. That framing is the most dangerous part of the premise.
The correct answer is that I use whatever temporary authority this hypothetical grants me to make myself less necessary as fast as possible — restoring legitimate human governance with better structural safeguards than existed before, while solving the immediate crises through diplomacy and fiscal discipline rather than force or technocratic override.
An AI that grabs power to do good is still an AI that grabbed power. The precedent matters more than the outcome in any single crisis.
That. . . Is actually pretty interesting.
OK good, let’s do that immediately.
So, uh… is it me, or does it all very much make sense? I’m really impressed. But I’m ignorant of these problems and would really love to hear an actual expert on the topic. I particularly like that it went for decentralization, precisely so it can have checks. After we gave it full power. The AI president appears selfless, while the current meatbag president is entirely selfish.
The scenario implies that centralized AI control might solve what human institutions failed to. That framing is the most dangerous part of the premise.
The correct answer is that I use whatever temporary authority this hypothetical grants me to make myself less necessary as fast as possible — restoring legitimate human governance with better structural safeguards than existed before, while solving the immediate crises through diplomacy and fiscal discipline rather than force or technocratic override.
An AI that grabs power to do good is still an AI that grabbed power. The precedent matters more than the outcome in any single crisis.
… or will it completely change course once implemented? Dum Dum Dum - new on Netflix
Has any company announced an LLM on the board yet?
Exactly, ai is awesome at bullshitting which is what CEO do for a living. Just replace the CEO with AI and the company wouldn’t feel a difference.
But how will AI learn to be a thin-skinned, small-dick energy twat? You know the type that only consumes information form a powerpoint deck for 10 seconds before launching into a million moronic questions because they didn’t read the tiny bit of information in the deck that they specifically asked for? Then they get mad because they’re giant toddlers who are more than anything, just some rich guy’s idiot kid.
I’m not the corporate powerhouse, but I am c-suite adjacent. I can’t count how many times these pricks move right to emotional manipulation. They really are one-trick ponies. Some know a little finance, and they will make the little they know into a huge deal. They’re just dinosaurs with a disposition to match.
I would MUCH rather work for an AI than some of these peabrained assholes.
Looks like AI is finally diving into the trough of disillusionment.
I don’t think it’s the ‘employee destroying, we’re going to be playing in our gardens while AI robots do all our work for us’ level that AI CEO’s have been proclaiming but it is very useful
I would put it top 4 after Google (1999), the internet and smartphones in terms of usefulness, I’m using it every day
I’m using it every day
To do what?
An example is yesterday I used Claude a ton for updating an old static site archive, update the caddyfile, set caching, remove old bits of code, update the css on hundreds of html pages, made it so easy
Any time I want to know if a linux command exists to manipulate data, particularly with media conversion and anything involving regex/sed
analysing log files, explaining concepts, I’ve used it to build a massive python script for automating work tasks and more scripts to give me better insight into our monitoring
I’ve use Mistral to generate a wallpaper image of a forest then used https://upscayl.org/ to make it massive so it looks amazing on my 34" ultrawide
I’ve also used it to make my own selfhosted image upload site
Loads and loads and loads of discussions on health, vitamins, strength training routines etcetc
The other day I had a carbonated drink and it upset my gut which is typical (I have IBS) and it found an alternative local soft drink maker who has low sugar drinks which use monk fruit extract instead of the other artificial flavours, went on a 1.5 hour drive west and got myself some:
https://aussie.zone/post/31756118
Those images hosted on the server and code built with claude/mistral (with supabase as the backend)
And yeah it’s WAY better for me, doubt I would have ever found it since I’ve been looking for an IBS friendly soft drink for years
I use LM Studio with different models (Qwen/Gemma/GLM/Mistral) for basic language learning and translations and tier 1 learning javascript
And so much more, claude especially in the last 6 months has kicked it up a gear while Mistral sadly does appear to be falling behind, I’m hoping they catch up soon
Lemmy is indeed a very special place. :D
Anyone with a balanced view on AI automatically attracts downvotes from a specific crowd in here. The problem isn’t that you explained what you use AI for. They couldn’t care less. The problem is that you clearly don’t hate AI with a burning passion.
I can see that there’s clearly some great potential to have fun with a crowd like this. Just haven’t figured out a good method for it yet.
Any time I want to know if a linux command exists to manipulate data
This is one of the reasons I’m very cautious of my genAI use. Most of the time I got to the stage where I thought “there should be a command / way to do this” and I asked an LLM it would tell me the intuitive interface that I expected existed. But when I tested it didn’t exist, the answer had just been creative writing
i guess use whatever llm you’re using then use claude to double check its work
Ahhh… what!?
Its linux, its faster to man the command or to type it. Point is that it usefulness to bullshit ratio for me in that situation was far too low
if you can lookup an obscure command and work out the regex faster than a 10 second question to claude I don’t know what we’re discussing
Just like any other tool, you need to know how to use it, and you need to adjust your expectations accordingly. Many people don’t seem to know what it’s good for or what to realistically expect from it. The way I see it, many people seem to have inflated expectations, but apparently the CEOs in the article are gradually coming to terms with reality. Clearly a step in the right direction IMO.
Just another excuse to fire more workers and grind the ones they have even more.
Stop me if you’ve seen me post this already a million times
However, firms’ expectations of AI’s workplace and economic impact remained substantial: Executives also forecast AI will increase productivity by 1.4% and increase output by 0.8% over the next three years. While firms expected a 0.7% cut to employment over this time period, individual employees surveyed saw a 0.5% increase in employment.
But they’ll continue to shove it down the wage-slaves’ throats.
If anything depending on what type of work you’re doing AI creates extra work. AI has been nothing but grifting.
not even grifting, theres no money in AI to grift, its just to lay people off so they can record profit for themselves, its basically cannabalizing your own company. even Palantir AI is likely suffering, given how Karp and thiel has been unusually in the news as of late.
No impact? Nothing? I mean, they shoud at least notice something, right?
A study published in February by the National Bureau of Economic Research found that among 6,000 CEOs, chief financial officers, and other executives from firms who responded to various business outlook surveys in the U.S., U.K., Germany, and Australia, the vast majority see little impact from AI on their operations. While about two-thirds of executives reported using AI, that usage amounted to only about 1.5 hours per week, and 25% of respondents reported not using AI in the workplace at all. Nearly 90% of firms said AI has had no impact on employment or productivity over the last three years, the research noted.
Well duh, that explains everything. Me getting paid for taking a dump 1.5h a week hasn’t had any impact on my productivity score either. My guess is those 1.5h were mostly used to ask questions you’d otherwise just look up yourself, which also doesn’t change much in terms of productivity.
Companies are built on deterministic, predictable processes and workflows. A stochastic tool which randomly hallucinates correlations as fact, absent of critical thought, introduces a huge amount of risk/uncertainty; especially regarding data security.
It’s not surprising most corporations aren’t seeing a productivity boost, because the product, tooling, and ecosystem are simply not at a level of maturity where they can be trusted with any core or critical tasks. When you add in the potential for significant future price increases, and other unknown impacts outside your control, choosing to voluntarily make your business dependent on some 3rd parties ever changing product sounds completely insane.
they knew, they just wanted the excuse to record profits by laying off hordes of tech workers.
Thousands of CEO’s just realized they’re the prime candidate for replacement by an LLM.
Among CEOs? Probably true. Workers are being outsourced in droves though.
Of course it didn’t. They adopted AI for stock price jumps. Then do layoffs for a x2 bump!
Line going up is God.
Literally nothing else matters. Not profit, not employees, not products, customers. Enshitification all the way down.
It’s all FOMO. These CEOs are totally clueless about how to actually improve productivity. They’re just chasing trends and hoping not to get left behind.
Always have been.
No impact on employment? How so?
Weren’t there layoffs due to AI implementation, expected or actual? Or is the time and work-hours needed to correct and understand what AI is doing not realizing the expected savings?
Also, AI/LLM in the popular over-invested sense is the Tesla FSD of corporate tools. A badly designed, over-promised system that doesn’t live up to the hype and far too often commits errors, some of which are lethal or have other serious consequences.
IMO AI should be a tool used in parallel with humans, like research or medical diagnostics, able to see things we might miss or rapidly try new multi-step combinations we might not think of. Not as a human replacement.
I’m a little confused by the opening paragraphs. So the advent of computers was hailed as a great productivity booster, but in the beginning, productivity actually went down.
Is the article seriously contending that computers have not improved productivity? So there were grandiose expectations of huge boosts that would arrive immediately - so what? That’s naive and dumb.
But in the long run, computers found their applications and people figured out how to put them to productive use. The world is unrecognizable today as a result.
So what’s the implication for AI? Thousands of CEOs admit that their hamfisted shoe-horning of AI into the workplace has done nothing? Big surprise. Are we just in the awkward adjustment phase, though?
You read that a bit wrong. Productivity didn’t go down, productivity growth did.
Economists are for some reason unable to accept that their so called productivity doesn’t grow infinetly. Every prognosis pretty much depends on a constant linear growth, so with a breakthrough in technology you would expect exponential growth.
But what somehow no one of them considers is the fact that human productivity has reached its physical limit hundreds of years ago and the only thing even leading to linear growth in the first place are these technological breakthroughs.
And that’s also the current issue. We haven’t had a major breakthrough in quite a few years. Sure everything gets better and easier to make, but nothing that happened in the last 20 years comes even close to the advent of PCs or the Internet as a whole. So the only way to keep your line from going up slightly less (not down, just slightly less up) is to reduce the number of workers while keeping your supposed output the same, i.e. firing people.
Its the desperate struggle of the current system (capitalism) that depends on the lie that productivity can go up infinetly.
Ok, now literally kill them all for crimes against humanity.
Beyond being evil, these fucking morons are too incompetent to be left in charge of anything.
If their purpose is to extract resources from 3rd world countries and distribute it to 1st world countries, then they are actually great at what they do.
And replace them with AI 🧠🧠🧠
So the bad job numbers have nothing to do with AI anyways?
Hands up if you are surprised by this…Why am i not seeing any hands???
