Spyke

Replies

Comment on

stop asking for a karma system

The Karma system was never a great system, I thought. Due to group think on Reddit, at times people get downvoted for no good reason. I think it's good to have a little diversity and not just have a model. I like Lemmy so far a lot and I think it is getting better and better. This is exactly how red it should have been, but they ruined it, of course.

news

Comment on

More Gen Z Americans identify as LGBTQ than as Republican

Reply in thread

I'm voting for Biden unless there's another nominee that will be the predominant choice against Trump. I don't like either of them but the choice is easy. Biden can't win my state, but I'm still going to vote for him literally just because he is running against Trump. I might cow about how I ate the Dems won't run on much else, but the contrast is big this time. It's always been really though, the Dems should be our new right wing party and a new farther left party like the Green party ought to be the more leftist faction. Dems to me already are neolibs with a neocon leaning. Leftist Populism must be embraced by the neolibs long term. Either way something has to give. Too much wealth to go around (even globally). The greedy old ideologies of constant growth at the expense of the poorest people in the world can't go forever. Growth economics can't go forever either. I have hope. Just go vote because that's what we can do easily as a minimum effort.

Comment on

Thousands of CEOs admit AI had no impact on employment or productivity

Reply in thread

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?

  1. 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.

Comment on

Microsoft paid $13B for this tech

It's amazing how Microsoft can take good models and absolutely ruin them in production... ChatGPT isn't perfect but it's like the difference between talking to the wall and talking to an avg IQ person that has reasoning capabilities in many domains that equals or exceeds human performance, if the user knows how to get the best prompt. That changes a little every time they do major model updates though.

I've had more intelligent conversations with my own computer running a 3 billion parameter open source model. They must be wasting an incredible amount of money. Especially with GPT-4 considering it produces pretty shit results through Bing Chat...

world

Comment on

Population tipping point could arrive by 2030: global fertility will drop below replacement level years earlier than expected.

Reply in thread

This is in the good economies too! In most of Africa life is even shittier. I can only imagine. Well, is still mostly better than it's ever been. History is cruel, and present but at least % of population living decent is much higher globally. Still, USA richest country in the world and we can't Even get universal healthcare, and instead of aiding homeless domestically, or money for food abroad etc.... We give a genocidal maniac hundreds of billions to play with.