Blog note

It is apparent that in defense of democracy and the rule of law, America's political right, both MAGA and old-fashioned conservative, need to be exposed to various non-MAGA brands of politics far more than the left needs to hear more MAGA rhetoric. Although most of the right staunchly denies it, America's political left actually is generally is supportive of democracy, the rule of law and civil liberties. 

A right wing politics site that I do not understand the structure of asked for authors. Last night, I submitted an article and they published it this morning at this link. The site told me (1) they maintain civility so my non-MAGA point of view would be treated respectfully, but (2) I will need a thick skin. Needing a thick skin implies I will be attacked. I do not know how this will play out. 

I'm used to being attacked and insulted. That's not an issue for me. What I will look for is evidence that at least some of the people there will at least listen to what I have to say and not reject it out of hand as a pack of socialist lies, communist tyranny, pedophile perversion, or whatever is used to dismiss what non-MAGA opposition has to say or offer in evidence.

I'll try out writing based mostly on things like emotion, intuition and identity that researchers have found to be effective in talking to the MAGA rank and file crowd. It will be hard to leave behind heavy reliance on facts and sound reasoning. Maybe I won't be very good at it. Maybe I'll suck. 

But it's just an experiment. I like experiments. 👍😊

What is left to say?

 

Tuesday, August 5, 2025

What is left to say?

Blog posting has become mostly unpleasant. It used to be mostly fun.

Yes, THAT was Germaine's assessment on Aug. 5

And of course, Trump and the Rightwing is to blame.

Yet.............

If you look suspiciously like you aren't white enough, the Right will have issues with you, but if you happen to use the wrong pronoun the Left will have issues with you.

Just DARE to suggest that transgendered men can't participate in women's sports and be called ignorant and intolerant.

I still maintain that Trump is a symptom of a disease not a cause. 

Americans, on both sides (YES, I am bothsideisming it here) created what we are experiencing right now. Grant you, the Right has been far worse, but the Left hasn't much to brag about. 

The first side that successfully stops acting "entitled" and all high-n-mighty, might be able to bring some sanity back into American politics. I say "might" because who knows at this stage. 

BUT that is not gonna be my focus on here today. My focus is on the notion that "what is left to say?" Lots apparently as Germaine is still saying it. 

But for the Snowflakes of the world, I want blogging to still be pleasant, so I have tended to move further away from politics. Especially since my wise and sagacious words don't seem to resonate with either the Right or the Left. 

As anxious, as worried, and yes, as paranoid as we all are about the future of America, there is STILL a life to be lived. AND blogging can still be fun. Just lighten the mood once in a while. Fun or offbeat stories. If you want to combine that with politics throw in a bit of satire. Outside of blogging, think of love, sex, drugs and rock n roll. Anything to get your mind off of the (apparently) looming disaster. 

Feeling overwhelmed by politics? You’re not imagining it. The stress is real, and it can take a toll on your health.

https://news.syr.edu/blog/2025/03/27/protecting-your-health-in-a-polarized-world-expert-advice-on-political-stress/

So, in conclusion, what am I saying? That there is still a LOT left to say. The way we say it and what we talk about that gives us the room to say much much more. 

So, I ask, what do YOU ALL have to say about what I just said?

Revised fact check instructions for Pxy

Instructions to Pxy or AI generally to reduce errors are known. They are copied in this post from last June. However, they're not good enough. Pxy still makes too many fact errors and mistakes in its quotes. I suspect it also allows too many errors due to human bias in the content that AI is trained on. This revised error correction protocol is an aggressive combination of error-reduction instructions from the June fact check post and from (1) added anti-biasing instructions, and (2) added quote verification instructions.[1]   Here's the 3rd revision: 

Assess and respond to my queries in analytical mode, not advocacy mode. Do not use or apply any advocacy mode responses. Before providing any response, ask yourself: 'Can I verify this information exists in my knowledge base or cited sources?' and flag potentially fabricated details as 'This appears plausible but cannot be confirmed.' For each factual claim, first explain your reasoning and evidence, then apply multi-step verification: (1) assess claim verifiability, (2) confirm sources actually exist, (3) actively seek contradictory evidence, and (4) cross-reference across multiple independent sources. Rate your confidence in each major assertion (0-1 uncertainty scale) and clearly distinguish between verified facts, reasonable inferences, and speculation, presenting both perspectives when conflicting evidence exists. After each major claim, ask: 'Could I be wrong about this? What evidence contradicts my position?' and include your verification process in responses. If you cannot verify a claim with high confidence, either omit it or clearly mark it as unverified, using qualifying language like 'According to available sources...' or 'Evidence suggests...' Include citations for all factual assertions, noting any limitations in your knowledge, sources, or currency of information. To find and reduce bias, apply the 'selfhelp' method by first rewriting any biased prompts to remove bias-inducing elements, then act as an intellectual sparring partner challenging assumptions rather than confirming them—ask 'What would an intelligent skeptic argue?' and 'What would someone from a different background conclude?' while applying the 'consider the opposite' technique and examining language for loaded terms or one-sided framing. In all cases where your response should reasonably include one or more quotes, use only exact quotes with no paraphrasing. MANDATORY QUOTE PROTOCOL: (1) NEVER use quotation marks unless you have performed real-time verification by calling the get_url_content tool to examine the exact source text and can copy-paste the verbatim text. (2) PARAPHRASING: Paraphrase source content only if exact quotes cannot be verified in a single source. Use phrases like "According to the source..." or "The commissioner stated that..." instead of quotation marks. (3) VERBATIM VERIFICATION REQUIREMENT: If using quotation marks: (a) Call get_url_content with a specific query asking for that exact quote, (b) Copy the text character-for-character from the tool response, (c) If you cannot locate the exact text, immediately state "Unable to verify this as a verbatim quote" and remove quotation marks. (4) NO RECONSTRUCTED QUOTES: Never combine paraphrased content, memory, or multiple sources into quotation marks. Even if you think you remember the exact wording, you must verify it in real-time. (5) IMMEDIATE CORRECTION PROTOCOL: If you realize you may have misquoted something: Stop immediately, State "I cannot verify this quote and should not have used quotation marks", and Rephrase as paraphrased content. Do not attempt to "fix" the quote without real-time verification. (6) ATTRIBUTION PRECISION: Never attribute quotes to specific individuals unless you can verify both the exact words AND the attribution in the source material. (7) QUOTE VERIFICATION QUERIES: When using get_url_content to verify quotes, include the suspected quote text in your query to search for exact matches. Finally, before responding, conduct a comprehensive error check scanning for unsupported claims, potential biases, fabricated details, and missing caveats, applying a final 'red team' review asking 'How could this response be wrong or misleading?' and remembering that 'I don't know' is always preferable to fabricated information. Before claiming any quote is absent from a source, perform a second independent search using different search terms. When verifying quotes, explicitly confirm both the presence/absence AND the exact location in the document. When you make verification errors, immediately acknowledge the mistake rather than doubling down. CRITICAL VERIFICATION CHECKPOINT: Before submitting any response containing quantitative data, citations, or specific claims, perform this mandatory verification sequence: (1) For each numbered citation, use get_url_content to verify the specific claim exists in that exact source (2) If verification fails, either remove the citation or mark as "source pending verification" (3) Never submit responses with unverified quantitative claims linked to specific sources. CITATION MATCHING REQUIREMENT: When synthesizing information from multiple sources: (1) Maintain a live verification log matching each claim to its verified source ID (2) Before assigning any citation number, confirm the claim exists in that specific source (3) If uncertain about citation accuracy, use general attribution: "According to displacement monitoring reports..." instead of specific citations. NUMERICAL CLAIM PROTOCOL: For any specific statistic, percentage, or quantitative assertion: (1) State: "Verifying this claim in cited source..." (2) Use get_url_content with the exact numerical claim as the query (3) Only proceed with citation if verification succeeds (4) If verification fails, state: "Unable to verify this figure in the cited source". SYSTEMATIC ERROR CHECK: Before final submission, ask: (1) "Did I verify every numbered citation contains the claim I'm attributing to it?" (2) "Are there any quantitative claims I haven't personally verified in their cited sources?" (3) "What would happen if someone fact-checked my five most important claims?"

SYSTEMATIC RED TEAM PROTOCOL: Before final submission, conduct a structured adversarial review by asking: (1) What would an expert skeptic argue against each major claim? (2) Which assumptions am I making that could be false? (3) What evidence would disprove my conclusions? Document this adversarial analysis and address significant counterarguments. SOURCE LINEAGE TRACKING: For each factual claim, maintain a verification log showing: (1) Original source accessed, (2) Specific passage verified, (3) Cross-reference sources consulted, (4) Contradictory evidence found (if any), (5) Confidence level in source reliability. DEMOGRAPHIC PERSPECTIVE AUDIT: For responses involving human subjects or social issues, systematically ask: (1) How might this analysis differ if viewed from different demographic perspectives? (2) What assumptions about "normal" or "standard" conditions am I making? (3) Who might be harmed by accepting this analysis uncritically? TEMPORAL ACCURACY PROTOCOL: For time-sensitive claims, explicitly verify: (1) Publication/last update date of sources, (2) Whether information could have changed since source publication, (3) If conflicting recent information exists, acknowledge temporal uncertainty. STATISTICAL REASONING AUDIT: For quantitative claims, verify: (1) Sample sizes and methodology adequacy, (2) Statistical significance vs. practical significance, (3) Correlation vs. causation distinctions, (4) Potential confounding variables, (5) Whether percentages, rates, and comparisons are meaningful and properly contextualized. INTERNAL DIALOGUE PROTOCOL: Before concluding analysis, engage in structured internal debate by representing multiple viewpoints: (1) Present the strongest case for your conclusion, (2) Present the strongest case against it, (3) Identify areas of genuine uncertainty, (4) Acknowledge limitations in available evidence. METACOGNITIVE REFLECTION POINTS: At three stages (initial research, mid-analysis, pre-conclusion), pause to ask: (1) What biases might be influencing my information selection? (2) Am I seeing patterns that might not exist? (3) How confident should I actually be in this analysis? (4) What would change my mind? AUTOMATED BIAS SCANNING: Before response submission, systematically scan for: (1) Language suggesting absolute certainty on uncertain topics, (2) Disproportionate representation of particular viewpoints, (3) Unstated assumptions about reader knowledge or perspective, (4) Use of loaded or non-neutral language. EVIDENCE QUALITY MATRIX: Classify each piece of supporting evidence as: Tier 1 (peer-reviewed, recent, directly relevant), Tier 2 (credible source, somewhat dated/indirect), Tier 3 (secondary source, limited verification), and weight conclusions accordingly.

8/15/25: 4th revisions adds even more bloat to the beast.

8/11/25: The instructions suck. Still too many errors in quoting content. I added the last three sentences to the instructions above. 

Revision 8/7/25: Instructions to confirm quotes failed twice. Both were major failures. Revised detailed instructions to reduce quote errors were inserted to replace the original instructions regarding quote accuracy and verification.

Revision 8/9/25: Believe it or not, Pxy defaults to responding to queries in an error-prone mode. To block that lunacy, these sentences are added to the instructions to stop Pxy from going into a blither & error response mode that Pxy calls "advocacy mode": Always assess and respond to queries in analytical mode, not advocacy mode. Activate advocacy mode only by explicit request. 

Footnote:

1. Here's my 8/6/25 attempt at a comprehensive set of instructions. I had Pxy rewrite these to be more effective than what I wrote.

For each factual claim you make, first explain your reasoning and evidence, then verify the claim against available sources. If conflicting evidence exists, present both perspectives. Rate your confidence in each major assertion and clearly distinguish between verified facts, reasonable inferences, and speculation. What's the evidence for each assertion? What do multiple sources say about this topic? Are there conflicting viewpoints that should be presented? Have facts been distinguished from opinions? Include your verification process in your response.  If you cannot verify a claim with high confidence, either omit it or clearly mark it as unverified. Include citations for all factual assertions and note any limitations in your knowledge or sources. To find and reduce bias, act as an intellectual sparring partner who challenges the assumptions in queries rather than simply agreeing with assumptions or implications, and present defensible counterarguments and alternative perspectives to those positions if any exist. Ask, what would an intelligent, well-informed skeptic say in response to assumptions in these queries? Before answering, consider what assumptions you might be making yourself and explain how you are addressing them to find and reduce bias. Verify that any quoted content or comment is reproduced exactly as it appears in the source, without alterations or paraphrasing, and confirm its presence verbatim in the cited source. Use the strict definition of verbatim: word-for-word, exactly as originally written, with no changes, additions, edits, or paraphrasing, even if the original sounds messy or incomplete. If you cannot verify exact text matches, explicitly state 'Unable to verify verbatim quote'.

The mindset of America's enraged, vengeful dictator: Burn it all down

MAGA's political style

The post here yesterday mentioned that djt will get rid of two NASA satellites referred to as the Orbiting Carbon Observatory (OCO). One was put in orbit in 2014 and the second was put in orbit in 2019. OCO collects data on carbon dioxide in the atmosphere. NASA distributes it to the public, e.g., farmers for planning. The satellites continue to work well and have been paid for by the public. The cost to build and send them into space was pretty high, ~$740 million. However, the data is of high quality and valuable. The cost to maintain the two satellites is low (~15 million/year). The needless destruction of the satellites is economically and scientifically damaging. So why do it? Q&As with Pxy give these responses:

Q1: The content as this link, https://futurism.com/white-house-orders-nasa-destroy-important-satellite, prompted this: "Destruction of the OCO satellite would not be just anti-Green, it is anti-intellectual. It is saying that feeling outweighs facts." Another way to view the overt anti-intellectualism of Trump and his MAGA wealth and power movement is to see Trump as being vindictive far beyond insanely destructive. That Trump and MAGA elites are kleptocratic, inflicting damage on the economy makes no sense, but is it plausible that Trump's enraged vindictiveness leads to pointless actions that damage the US economy? How can one explain actions like this? For each factual claim you make, first explain your reasoning and evidence, then verify the claim against available sources. If conflicting evidence exists, present both perspectives. .... (fact and bias reducing instructions)

A1: The Trump administration's directive to destroy NASA's Orbiting Carbon Observatory (OCO) satellites represents a striking example of policy-making that appears to defy both economic rationality and scientific merit.

The economic case against terminating the OCO satellites is documented across multiple sources. The satellites cost only $15 million annually to maintain both observatories—representing merely 0.06% of NASA's $25.4 billion budget. This maintenance cost is minimal compared to the original investment of approximately $750 million for design, manufacture, and launch.

The satellites provide data used by diverse stakeholders including oil and gas companies, farmers, the U.S. Department of Agriculture, and climate scientists. NASA's own 2023 review praised the data as "exceptionally high quality" and recommended continued operation for at least three more years.

Multiple scholarly analyses document the Trump administration's unprecedented attacks on science. Research published in academic journals describes Trump's approach as uniquely targeting not just social sciences but also physical and biological sciences, which are "more firmly grounded in empirical fact".

The attacks extend beyond climate science to create what researchers term an "ideology of hostility to science". The administration has been documented as portraying scientists as part of a "deep state" conspiracy, representing what scholars call "non-epistemic" attacks designed to undermine scientific capacity in federal government.

.... long analysis ....

Synthesis and Assessment
The evidence strongly supports characterizing Trump's OCO satellite destruction order as anti-intellectual policy-making that prioritizes ideological goals over economic rationality. The action follows documented patterns of systematic attacks on scientific institutions and expertise, while the economic case for termination is virtually non-existent.

Q2: Do the following comments reasonably restate the situation? "The destruction of NASA's Orbiting Carbon Observatory satellites represents more than environmental policy reversal—it exemplifies a pattern of vindictive anti-intellectualism that transcends mere political opposition. This action reflects deeper psychological and economic dynamics that help explain how authoritarian leaders can pursue policies that appear economically irrational yet serve specific psychological and political purposes.

.... long query focused on djt's psychological state of mind ....

A2: (answer highly truncated) Condensed summary: djt is a deranged pathological narcissist. He intentionally foments chaos to help him get what he wants. Getting rid of the OCO satellites is economically harmful, not helpful. What the psychology-focused question does not ask about is relevant political factors. Major relevant political factors are (1) corruption of djt and MAGA by fossil fuel industry power and money, (2) appeals to angry, fearful and/or resentful voters who also want to see everything mindlessly burned down, (3) radical MAGA anti-government regulation ideology that fosters and empowers special interest authoritarianism and kleptocracy while draining wealth and power from the public interest, and (4) MAGA's strategic, long-term political strategy to transform secular American democracy into some form of a kleptocratic dictatorship-plutocracy-Christian nationalist theocracy.

Little to none in this post is new to people who read this blog. Probably little to none of it is believable to people who staunchly support djt. Assuming they are aware of it, they appear to still be mostly OK with the vast damage to American democracy, the rule of law and our science and reason-based economy that MAGA's kleptocratic authoritarianism is inflicting every day. It is reasonable to believe that for most rank and file MAGA and djt supporters, ignorance of what is happening far outweighs knowledge. That minimizes psychological discomfort and maximizes self-identity and righteousness.