strappingfrequent
No bio...
User ID: 1155
strappingfrequent
1mo ago
**If the rate of change in AI increased, for example, if a company revealed a powerful new AI
that placed in the tenth percentile on the BAR and then released an even more powerful new
AI three months later that placed 90th percentile on the BAR... How would that influence your
perspective?**
If the rate of change in AI increased dramatically, as described in your example, it would significantly
impact my perspective on the potential threats to the United States as a way of life. Here's how it
would alter the rankings and probabilities:
1. Artificial intelligence and automation (High probability): The rapid advancement of AI
technology, demonstrated by a company releasing two powerful AI systems in quick
succession, would suggest that the potential risks associated with AI and automation are
more imminent than previously anticipated. These risks include job displacement, economic
inequality, ethical concerns surrounding AI usage, and potential AI misuse by malicious
actors. The rapid development of AI would necessitate immediate attention to establish
proper regulations, ethical guidelines, and workforce transition plans.
2. Cyber warfare and cyberattacks (High probability): The rise of advanced AI technology
would also increase the risk of cyber warfare and cyberattacks, as AI systems can be used to
conduct or defend against these attacks. The integration of AI into cyber operations could
lead to more sophisticated, targeted, and difficult-to-detect attacks, posing a significant
threat to critical infrastructure, national security, and privacy.
3. Bioterrorism and pandemics (Medium-high probability): The rapid development of AI could
also influence the fields of biotechnology and synthetic biology. Advanced AI systems may
accelerate the development of new drugs, therapies, and biotechnologies, but could also be
misused to create dangerous pathogens or biological weapons. While the probability
remains medium-high, the risks associated with AI-enhanced bioterrorism would warrant
increased vigilance and investment in biosecurity measures.
4. Political instability and social unrest (Medium-high probability): With AI and automation
disrupting the job market and potentially exacerbating income inequality, there is a
heightened risk of political instability and social unrest. The rapid development and
implementation of AI technologies may lead to public anxiety, mistrust, and social divisions,
contributing to an overall increase in the potential for instability and conflict.
The other threats mentioned in the previous analysis (climate change, economic collapse, nuclear war
or nuclear terrorism, and extraterrestrial threats) would remain significant but would not be directly
influenced by the rapid advancement in AI technology. However, advanced AI could also have
indirect effects on these threats by impacting decision-making processes, resource allocation, and
global cooperation on various issues.
In conclusion, the rapid advancement of AI technology would elevate the significance of AI-related
threats and necessitate urgent policy and regulatory responses to address the potential risks and
implications for the United States as a way of life.
Excellent. Please do the same for existential threats to the United States as a way of life.
Here is a ranked list of existential threats to the United States as a way of life, along with the
probability of occurrence and evidence to support the conclusion. Note that these probabilities are
estimative and should be interpreted with caution.
1. Climate change (High probability): Evidence: The scientific consensus is clear that climate
change is happening and is largely human-driven. The impacts include more frequent and
severe weather events, sea-level rise, and disruptions to agriculture, which can lead to food
and water shortages, economic instability, and displacement of populations.
2. Cyber warfare and cyberattacks (High probability): Evidence: The increasing reliance on
digital infrastructure and technology makes the US vulnerable to cyberattacks from nationstates and non-state actors. Examples include the SolarWinds hack in 2020 and the
WannaCry ransomware attack in 2017, which caused widespread disruption.
3. Bioterrorism and pandemics (Medium-high probability): Evidence: The COVID-19 pandemic
demonstrated the vulnerability of societies to global pandemics, with significant loss of life
and economic consequences. Bioterrorism, involving the deliberate release of viruses,
bacteria, or other germs, could have similar catastrophic effects.
4. Economic collapse (Medium probability): Evidence: The Great Recession of 2007-2009
showed that economic crises can have profound impacts on the United States' way of life.
Factors such as high levels of national debt, income inequality, and global economic
interdependence can contribute to economic instability.
5. Nuclear war or nuclear terrorism (Medium-low probability): Evidence: The potential for
nuclear conflict or terrorism remains a significant existential threat, even though the
probability of a large-scale nuclear exchange has decreased since the Cold War. The
proliferation of nuclear weapons and materials increases the risk of accidental or intentional
nuclear incidents.
6. Artificial intelligence and automation (Low-medium probability): Evidence: Rapid advances
in artificial intelligence and automation could lead to significant job displacement and social
unrest. If not managed carefully, these technological advancements could exacerbate
economic inequality and destabilize the social fabric of the United States.
7. Political instability and social unrest (Low-medium probability): Evidence: While the United
States has a long history of political stability, recent events, such as the 2021 Capitol
insurrection, highlight the potential for social unrest and conflict. Deepening political
divisions and erosion of trust in institutions can contribute to instability.
8. Extraterrestrial threats (Low probability): Evidence: While the probability is low, potential
extraterrestrial threats include asteroid impacts or contact with hostile extraterrestrial
civilizations. NASA and other space agencies are working to identify and track potentially
hazardous near-Earth objects to mitigate the risk of impact
My grandfather quickly intuited the ramifications of an LLM appraised at ~118 IQ. My grandmother insisted that Republicans were the true threat (to democracy). So... I consulted GPT-4. Note: GPT-4 training data is over a year old; so... two prompts to calibrate it's judgement followed by a hypothetical (which we just recently witnessed).
**You are the chief scientist responsible for a research center that employs the leading experts
across a wide variety of domains. You have been tasked to analyze potential threats to
democracy in the United States. Please provide a ranked list with probability as well as
evidence to support your conclusion.**
As the chief scientist, I have analyzed potential threats to democracy in the United States and ranked
them based on their probability of occurrence and impact. The evidence provided is based on historical
events, emerging trends, and expert opinions. Please note that these probabilities are estimative and
should be interpreted with caution.
1. Disinformation and misinformation campaigns (High probability): Evidence: The rise of social
media and the internet has made it easier to spread false information, propaganda, and
conspiracy theories. For example, the 2016 US presidential election saw widespread
disinformation campaigns, including Russian interference.
2. Partisan polarization and extreme partisanship (High probability): Evidence: Extreme
partisanship has led to gridlock in Congress, gerrymandering, and erosion of trust in democratic
institutions. The last two decades have seen an increase in political polarization in the United
States, as evidenced by voting patterns and opinion polls.
3. Foreign interference in elections (Medium-high probability): Evidence: There have been
documented cases of foreign interference in US elections, most notably the Russian interference
in the 2016 presidential election. The US intelligence community has warned of continued
attempts by foreign actors to influence American politics.
4. Erosion of trust in democratic institutions (Medium probability): Evidence: Trust in institutions,
such as the media, Congress, and the judiciary, has been on a decline for several years. The 2021
Edelman Trust Barometer reported that trust in institutions is at an all-time low in the US.
5. Voter suppression and barriers to voting (Medium probability): Evidence: Numerous states
have enacted restrictive voting laws in recent years, which disproportionately affect minority and
low-income voters. Examples include voter ID laws, voter roll purges, and reduced early voting
opportunities.
6. Economic inequality (Medium-low probability): Evidence: Widening income inequality can
exacerbate social and political divisions, leading to decreased trust in the democratic process.
According to the Economic Policy Institute, income inequality in the US has been on the rise since
the 1970s.
7. Cyberattacks on election infrastructure (Low-medium probability): Evidence: Although there
have been no successful large-scale cyberattacks on US election infrastructure, the potential for
such an attack remains a concern. The Department of Homeland Security has classified election
systems as critical infrastructure, and efforts to secure them are ongoing.
8. Breakdown of the rule of law (Low probability): Evidence: The United States has a strong
tradition of the rule of law, but there have been instances of political leaders attempting to
undermine or circumvent legal processes. Maintaining the independence of the judiciary and law
enforcement is crucial for the health of a democracy.
These are the most significant potential threats to democracy in the United States based on current
analysis. It is crucial to address these threats to ensure the continued stability and integrity of the
democratic system.
It's hard to imagine a plausible cessation of hostilities that isn't preceded by RUS regime change. Likewise, why would UKR or NATO agree? Russia already has imperiled demographics; the longer this war goes on the more they write themselves out of the future.
To answer your question -- if the war ended today; both Russia/Ukraine lose, NATO wins.
strappingfrequent
4mo ago
Well said.
The idea that Russia is winning or win an attritional war against a united NATO (more so than since the Berlin Airlift); I'm completely astounded that people can look at the last year and think Russia is a near-peer. They chose a blitz to Kiev because a long attritional war against a united NATO is precisely what they wanted to avoid.
NATO Goals:
-
avoid a large-scale nuclear exchange
-
prevent Russia occupation of territory that shares a border with NATO; related to point 1.
-
damage Russia enough so as to impact their ability to aggress in the future
What we see now is, literally, perfect. Ukraine would prefer a quicker resolution; they're paying in blood. But, unfortunately, there is no easy resolution here. For reasons I'll get to, I think NATO could amp it up a bit and absolutely defang Russia's capability to wage any sort of conventional war -- but that is a less-than-desirable outcome. A slow bleed is preferable than a Russia shocked into even more humiliation (and credible reasons to fear for it's own safety). If Ukraine is willing to fight -- and polling indicates that they are -- then NATO has no reason to disrupt this status quo.
Feel free to disagree with me; I'd like to hear opposing viewpoints:
Even if the US is limited to contributions of material, intelligence, and resources: I rate their current involvement a two out of ten. There are many, many options available -- the difficulty is finding the appropriate balance point between preventing a UKR collapse and accidentally going to far and causing the collapse of the entire Russian war effort.
Observations:
Intelligence/Precision Fires
-
They're slinging missiles at cities; this makes no sense at all unless they lack the capability to engage worthwhile military targets. When has strategic bombing ever actually worked? Strategic bombing of civilian centers is a (cold-blooded) gift to Ukraine; Zelensky's task of maintaining NATO support is easier when Kremlin TV runs segments of civilians shrieking in terror, bombs, and syncopated cheering. https://twitter.com/JuliaDavisNews/status/1580196518765551616
-
Despite Russia's claims, no visual evidence that they've destroyed a single HIMARS; I think the 80km precision fire capability is a genuine problem for Russia; note the quantity of destroyed C2 vehicles (visually-confirmed; https://www.oryxspioenkop.com/2022/02/attack-on-europe-documenting-equipment.html). This is weird; so is the quantity of KIA RUS field/general officers.
Kharkiv Offensive
-
This was a rout; the sheer quantity of abandoned material is absurd. 100+ tanks, 100+ IFVs, 80+ APCs, 60+ arty... and many of these were left in working order; i.e., Russian forces didn't even take the time to disable them.
-
Some of Russia's elite broke: T80s were recovered; only the elite get those. Specifically, 4th Guards Tank Army; stationed in Moscow... these are Russia's best.
NATO "shortage"
- This has got to be sheer cope; nothing contributed thus far (or ever) will actually weaken any NATO countries security posture. All this old stuff was kept around specifically for this purpose; e.g., fucking around in regional conflicts. And to say that NATO -- as a collective -- is incapable of diverting the resources necessary to produce more... how does that make any sense at all? GDP is a component of military effectiveness, and NATO enjoys a 15:1 advantage. Given the long-term attritional nature of the conflict thus far, even if Russia were to miraculously transform itself, pick up momentum, and even if they shifted to a full-scale war economy with no internal friction... this really changes nothing at all. To think that the US would just say "aww shucks; we're a bit low on arty shells, guess we lost" is ridiculous.
I have no doubt that if the US actually sent over the good shit, then in conjunction with the battle planning and intel... Russia's conventional force would be lambs for a slaughter. How could they maintain logistics for 300k+ combatants when every single GLOC is actively observed and within reach of precision munitions.
We'll know more over the next few months; mud season ends by May. Should Russia start gaining momentum, I'd expect to see more zany attacks designed to disrupt logistics/C2. Note: Russia withdrew from Kherson shortly after the Kerch Bridge was disabled. Critical GLOC.
strappingfrequent
4mo ago
Can't rhyme? A poet friend of mine was lamenting that it rhymes too much!
A whisper on air,
A silent thought
That lingers there.
Though none can hear
It still exists,
A hushed connection
Of souls that share.
Glorpth yoozled down the blizbevy tree, His muttazels aflutter with glee. Beside him stood the zibbablock, Gloating and ready with a shock. But the brave Glorpth didn't falter, He battled the beast with a clatter. He thrashed and he slashed 'til the night was done, And the Jabberwock was won.
I specifically asked for three nonsense words for this one...
Through the dark woods I heard a howl,
Flittering through like a silken owl.
The slonky creatures stirred below,
As they rose and began to flow.
Crossing through the gnelpy grove
I saw what I could not move.
It was covered in gloopy scales
And had a thousand hissy tails.
It was the jabberwocky, fierce and wild
Ready to attack with a baleful smile.
I ran and ran and never looked back
The terror of its presence slack.
strappingfrequent
5mo ago
Haha -- an absolutely fantastic mom & pop's breakfast diner near me has 4.7 (out of 5.0) on Google. They'd obviously rather get no review at all from you than receive a 4/5.
My guess is it's an emergent property with a self-sustaining feedback loop. If enough people are mapping a perfect score to "I was pleased" and the opposite to "I wasn't pleased" and most people are pleased, then you'd expect to see some sort of pareto distribution with a slight bump at the lowest.
Why do people do this? Not sure; maybe shared empathy from working customer-facing jobs. A server could knock it out of the park on a grueling horrendous shift for every customer but one; and that one customer leaving a scathing review online would seriously jeopardize the server's job. So, if I leave a review it's with perfect scores and if I mention names I'll speak of them with exuberant glowing language (even if they were just decent) because it may brighten someone's day a bit.
strappingfrequent
5mo ago
tldr: ridesharing apps offer rating systems out of 5 stars and anything other than 5/5 threatens the driver's longevity on the platform. I think at one point, ~4.7 was the cutoff. Local restaurant owners and other similar industries; a "bad string" of "bad" 4/5 reviews and The Algorithm rears its ugly head.
The USA tends to treat less-than-perfect scores as egregious failures. Two issues: enough people are somewhat conscious of the reality that, despite agreeing with your sentiment (it wasn't perfect; there's room for improvement; giving a 100 percent makes no sense), the choices available are "perfect" or "bad enough that I want to damage their bottom line." So we maintain the "perfect is the normal answer" -- but there's still enough people who aren't in the loop (or don't care) that they'll write a glowing 4/5 review for a local business not understanding how frustrating that must be for the proprietor: clearly the customer enjoyed their experience and plans to return... but a 4/5 just lowered the restaurant by seven positions on assorted metric consolidation sites... because the top 10 restaurants are all between 4.7 and 4.9 (for example).
strappingfrequent
5mo ago
Software Engineering
In my experience, DoD contractors pay SWEs pretty terribly in comparison to the private sector. They're constrained by how the DoD itself ascribes value (e.g., credentials and YoE). That being said, a month ago, a buddy of mine with a 3-month bootcamp "degree" got an offer from Booz Allen Hamilton for 80k hybrid (3 days in the office). Granted, that's not 100k, but as I told him... just get 1 YoE and job hop for a monstrous raise.
My company is much more selective; but ~100k (fully-remote!) would reasonable for an impressive junior.
And, for fun -- when I cut/pasted the entire previous page to Midjourney...
https://imgur.com/a/dXWsZFD
More options
Context Copy link