3
points
0xWTF
Joined 289 karma
- This reminds me of a couple things:
== Tim's Vermeer ==
Specifically Tim's quote "There's also this modern idea that art and technology must never meet - you know, you go to school for technology or you go to school for art, but never for both... And in the Golden Age, they were one and the same person."
https://en.wikipedia.org/wiki/Tim%27s_Vermeer
https://www.imdb.com/title/tt3089388/quotes/?item=qt2312040
== John Lind's The Science of Photography ==
Best explanation I ever read on the science of photography https://johnlind.tripod.com/science/scienceframe.html
== Bob Atkins ==
Bob used to have some incredible articles on the science of photography that were linked from photo.net back when Philip Greenspun owned and operated it. A detailed explanation of digital sensor fundamentals (e.g. why bigger wells are inherently better) particularly sticks in my mind. They're still online (bookmarked now!)
https://www.bobatkins.com/photography/digital/size_matters.h...
- The 14" MacBook Pro is unequaled as a daily driver. You can compile some things in a pinch, but let's face it, if you're writing compiled code professionally, someone in management owes your team build resources. Your laptop is your canvas, your easel, your blank page, your sketch pad, and your research library and research notebook. In 2025 and in 2026, your laptop is not for compiling.
- Histotripsy means "cell pulverizing". We know disruption (pulverization or otherwise) of a tumor bed tends to incite a local inflammatory reaction, and a brisk inflammatory reaction seems to correlate with survival. So the idea here seems to be an extension of high energy ultrasound methods developed for lithotripsy (breaking up kidney stones) to disrupt tumor beds. Not something I'd want for a pre-cancerous lesion, but if it's stage 4 liver mets ... sure. Have at it.
- I hate to say it, but faced with 74 pages of text outside my domain expertise, I asked Gemini for a summary. Assuming you've read the original, does this summary track well?
==== 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).
2. Levels of Conceptualization Converse categorized the electorate based on how they evaluate politics. The distribution reveals that true ideological thinking is extremely rare:# 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.
3. Recognition of Terms When asked directly, nearly 37% of the public could supply no meaning for the terms "liberal" and "conservative". Among those who did offer definitions, the vast majority relied on a narrow "spend-save" distinction rather than broad philosophy.# 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.
Conclusion: The "Issue Public"# 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?
- At this point I'm fairly senior and work directly with funding sponsors and requirements owners. The gal who 100% owns the problem, worldwide, says "I need X, how much it going to cost?", while X is a big, hairy ball of wax and I have 18 minutes left in the 30 minute meeting to get as many details as I can while I work up a guesstimate. Because the funding line will be decided by minute 30.
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.
- I mean, there's additional evidence https://unusualwhales.com/politics/article/congress-trading-...
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...
- For the uninitiated: https://www.reddit.com/r/restofthefuckingowl/
- Children do the same thing intuitively: parents continually complain that their children don't listen to them. But as soon as someone else tells them to "cover their nose", "chew with their mouth closed", "don't run with scissors", whatever, they listen and integrate that guidance into their behavior. What's harder to observe is all the external guidance they get that they don't integrate until their parents tell them. It's internal vs external validation.
- Ok, this seems like a good post. At the end of the day, what do I, as a single investor, do? I'm 50 years old, 2 kids in college, I have a $300,000 mortgage on a house presently worth $1M. I have $300,000 cash and an open eTrade account.
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.
- Sonova (Phonak's parent company) bought Sennheiser and you can now buy their Sonite R at Costco for $1600. If you have recent Phonaks, you'll recognize the design immediately. They also have an array of peripherals: https://www.costco.com/f/-/sennheiser-brand-showcase
- I usually look at garage sales as displays of things you shouldn't buy. I feel like this is even more ... that. It would be helpful if Amazon posted to the return rates of this stuff.
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?
- 17 points
- 5 points
- Depends on the market. Everyone dies eventually. Every near-fatal illness you suffer is a windfall for the medical system and ensures another windfall later.
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'?"
Coffee. Vols. 1–6. R. J. Clarke and R. Macrae. Elsevier Applied Science, 1985.
Coffee: Botany, Biochemistry and Production of Beans and Beverage. M. N. Clifford and K. C. Willson. Croom Helm, London, 1985.
Caffeine, Coffee and Health. Edited by S. Garattini. Raven Press, 1993.
Coffee: Recent Developments. R. J. Clarke and O. Vitzthum. Blackwell Science, 2001.
Espresso Coffee: The Science of Quality. Second edition. A. Illy and R. Viani. Academic Press, 2005.
Association for Science and Information on Coffee: www.asic-cafe.org (sadly now a spam/gambling site)
International Coffee Organization: www.ico.org (seems to have a bad cert now?)
News from the industry of specialty coffee: www.scaa.org/chronicle/category/coffee-science (also dead)
from https://www.scientificamerican.com/article/the-science-of-a-...