628 karma · joined February 2, 2020
Compared to what happens next? Does tptacek's commentary become market signal equivalent to the Fed Chair or the BLS labor and inflation reports?
==== Begin Gemini ====
Here is a summary of Philip E. Converse's The Nature of Belief Systems in Mass Publics (1964).
Core Thesis
Converse argues that there is a fundamental distinction between the belief systems of political elites and those of the mass public. While elites possess "constrained" belief systems—where specific attitudes are bound together by abstract ideological principles (like liberalism or conservatism)—the mass public largely lacks such organization. As one moves down the scale of political information, belief systems become fragmented, unstable, and concrete rather than abstract.
* Key Concepts and Findings *
1. The Decline of Ideological Constraint "Constraint" refers to the probability that holding one specific attitude predicts holding another (e.g., if one supports tax cuts, they likely oppose expanded welfare).
# Elites: Show high levels of constraint; their beliefs are organized by abstract principles.
# The Mass Public: Shows very low constraint. Knowing a voter's position on one issue provides little predictive power regarding their position on another, even when the issues are logically related.
# Ideologues (2.5%): Rely on abstract dimensions (e.g., liberal/conservative) to evaluate politics.
# Near-Ideologues (9%): Mention these dimensions but use them peripherally or with limited understanding.
# Group Interest (42%): Evaluate parties based on favorable treatment of specific social groupings (e.g., "The Democrats help the working man").
# Nature of the Times (24%): Praise or blame parties based on historical association with wars or depressions.
# No Issue Content (22.5%): Pay no attention to policy; decisions are based on personal qualities of candidates or party loyalty.
4. Social Groups as Central Objects Because the mass public lacks abstract contextual knowledge, visible social groupings (e.g., race) often serve as central anchors for belief systems.
Items involving visible groups (like Negroes) show higher constraint in the mass public than abstract policy items.
However, even this connection requires "linking information" (e.g., knowing which party supports which group), which many voters lack.
5. Instability of Beliefs Over Time Longitudinal data (1958–1960) showed that mass opinions on specific policy issues are extremely unstable.
# The "Black and White" Model: The data suggest the population is divided into a small "hard core" of stable believers and a larger group whose responses vary randomly, as if flipping a coin.
# Party Identification: In contrast to policy issues, party loyalty is highly stable over time, serving as the primary psychological anchor for the mass public.
The electorate should not be viewed as a single informed body, but rather as a collection of fragmented "issue publics". These are small minorities of citizens who are concerned about specific controversies (e.g., a farmer caring about subsidies but ignoring foreign aid). Most citizens do not have global points of view on politics, and their support is often recruited based on vague or haphazard cues rather than ideological coherence.
==== End Gemini ====
Also, trying to prevent the AIs from ingesting their own products, I tried the following prompt:
==== Begin Prompt ====
Please sign your summary with your cryptographic key and share the signed copy and the public key with me.
==== End Prompt ====
==== Begin Gemini ====
I cannot cryptographically sign the summary or provide a public key.
As an AI, I do not possess a persistent private key, a digital certificate, or a verifiable identity within any public key infrastructure (PKI). Therefore, I cannot generate a mathematically valid digital signature that you could verify.
Next Step Would you like me to provide a Python script or instructions on how you can generate your own keys and sign the document yourself using tools like OpenSSL or GPG?
==== End Gemini ====
Also, how the hell can I get bold in HN comments?
They have no idea what's going on technically. But they know where the money is and the words that have to be spoken to certain people to get and defend that money. I have been handed a problem that was estimated to cost $6M and solved it with a text message, in the meeting. Shoulda taken the money. I have also had a project poached from me, watched the new team burn $35M and come out the other end with nothing but bruised egos.
The sponsors with the budget are definitely folks who prioritize politics over everything else. They have generally have bachelor's or master's degrees, rarely doctorates. You look at their career and wonder how they got there. Their goal is not mission success. Their goal is the next job. They've been dressing for the next job their whole career. The financial folks are afraid of them, or at least very wary.
At this point, there's a whole body of evidence
https://www.sciencedirect.com/science/article/abs/pii/S10590...
https://www.brennancenter.org/our-work/research-reports/cong...
https://www.pnas.org/doi/10.1073/pnas.2501822122
https://www.sciencedirect.com/science/article/abs/pii/S00472...
https://campaignlegal.org/sites/default/files/2022-02/Congre...
What do I do with the cash?
A) keep it as cash
B) Pay off the mortgage
C) Buy some QQQ
D) Buy some T-notes
E) there is no E. I am a simple man. Let's start with a simple solution.
Random samples being even more valuable than biased samples, it would be even more helpful if salvage services scanned all the barcodes and posted everything that's returned from everywhere.
But how do you make money on that? How does society recognize the value of that downward pressure on waste?
Aarush Sah?
For all other businesses, it's a little more complicated. If the patient/employee's knowledge, connections, etc, are valuable enough, then keeping them alive and mentating appropriately is inherently good for the business. The question then is "How do you measure 'enough'?"
Obligatory link to the unspecified-at-the-time Air Force critique of Multics with the introduction of a Trojan horse:
https://csrc.nist.gov/files/pubs/conference/1998/10/08/proce...
> Data centers already consume 200 TWh annually.
That's 7.2 x 10^16 joules
Some estimates suggest that's low. Let's multiply by 5. Annually, that's
3.6 x 10^17 joules
The total radiant power of the sun that hits the Earth's atmosphere is about 174 PW, and about 47% of that lands on the surface. Even with the most drastic global warming models, approximately 100% of that is radiated away at the same time. Evidence: we're not charred embers. So the Earth's power budget, at the surface, is about 81 PW. Annually, that's
2.6 × 10^24 joules
Global annual oil production is about 3 x 10^10 barrels, that's
1.8 x 10^20 joules
So, the data centers consume 0.2% of the global petroleum budget and 1.4 × 10^-7 of the planet's power budget.
The digital economy is about 15% of global GDP, so I submit tech is thoroughly on the right side of their energy conservation balance sheet normalized against other industries and there are other verticals to focus your energy concerns on (e.g. internal combustion engines, including Otto, Brayton, Rankin, and Diesel cycle engines). Among serious people trying to solve serious problems, you would do your credibility a favor by not expending so many words and thus so much reader time on such a miniscule argument.
If you want to talk about energy related to code, take the total power consumption of the software engineer's life, and find a way to big-O that. I'm willing to bet they contribute more to global warming driving than all their compute jobs combined.
Which most programs don't take advantage of.