It seems even a group that purports to be rational critical thinkers don't want to be rational critical thinkers to the extent of looking into the root causes.

Comments URL: https://news.ycombinator.com/item?id=48816905

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48806886

Points: 3

# Comments: 0

"True" has a connotation of absoluteness and finality. But I doubt humanity can ever know what is "true" about the universe. We can only model its phenomena with better theories, where "better" is always a temporary badge conferred for its prediction power and degree of agreement with known observations. Until an even "better" theory is figured out.

"Now they just need to figure out which ones are _better_"

This seems to imply a social ideology rather than a geostrategic one. The term "Nazi" is used for a specific brand of social ideology, not a general term for imperialist policy.

Which policy rollbacks were you talking about?

They went to war to fight Germany's, Japan's, and Russia's attempts at geostrategic hegemony. If Germany, USSR, and Japan had stayed in their geostrategic lanes, they wouldn't have invited a war on them.

Every type of content will have some restrictions. Structural, ideological, financial.

Just about every type of written content on a platform has word limits imposed by its editors. Word limits restrict how much context can be provided in any single article.

Style guides, personal beliefs, management directives, and legal risks impose ideological and political restrictions. Even if an author is candid in the draft copy, reviewers and editors make them tone it down or tone it down themselves without asking the author.

Also doubtful whether a reputed university for elites like Yale will directly point fingers at the rightwing in power or at an elites' blueprint like Project 2025.

Personally, I think all these criticisms of this article are actually a form of centrist deflection and pretense. Centrists support rightwing policies but also don't want to come across as morally bad in such fora. So, to justify their centrism, they criticize the messengers through bikeshedding.

That's the problem.

> This article failed on any level to help me make an informed decision.

You shouldn't rely on just one article to make an "informed decision." Indeed, anyone who genuinely wants to make "informed decisions" must cultivate the habit of actively seeking out to be better informed rather than passively relying on a single article.

There's an entire chain of events that the links in this article lead to...

...The NSF is descoping.

...It's descoping because of federal funding cuts to science projects

...Federal funding cuts are due to the pro-fossil-fuel biases and climate change skepticism of the rightwing Trump admin and its backers. Their ideological strategy to redesign American society, Project 2025, specifically mentions disbanding this very monitoring project.

I was able to find that all out in about 15 minutes though I'm neither American nor reside there or anywhere close to it.

A performative pretense of informed decision making is not the same as genuinely making informed decisions.

That should be the assumption in an ethical society. Especially given the current economic context. Veil of ignorance principle.

> It makes it out to be unhireable charity cases.

Any "hireable" expert can run into bad luck. A person down on their luck doesn't imply "unhireable." Those recruiters who assume something so illogical - well, perhaps job seekers in this forum are overall better off without such illogical recruiters in the pool. If they make such a wrong assumption at the start, who knows what other illogical assumptions they'll make once the job starts.

> I have been lucky to find employment...

Irrelevant

However, your analogy is not equivalent to, nor an example for, what I said. There's a difference between a phone's own USB/audiojack interfaces and a wall outlet.

Most people know that just about every Android phone has a restricted hardware design, not an expandable one.

So, "turn your phone into X" is bound to automatically evoke images of another device that plugs into the phone via common connectors like USB or the audio jack and an app on the phone to control that device. That's what the phrase means to most people in the context of Android.

"Turn your phone into a ham radio transceiver controller" is neither needed nor entirely accurate, because then people will assume it can control _any_ ham radio transceiver.

1) perfect is the enemy of good

2) fake it till you make it

The analogies imagine difficult scenarios where the habit of taking shortcuts doesn't help. But most people most of the time don't run into those scenarios at all.

But what you said - "It's also because social media is part of the USA's soft power projection, and many of us now consider this to be a threat." - strikes me as the most plausible driver behind it, given how chummy Trump and the techbros have become.

I agree with your other observations about SM. But they've all been true from many years. That's why this sudden urge by culturally diverse societies to act now feels suspicious, to me at least.

Well, I happen to use it everyday. I honestly don't know what exactly is "terrible/horrible/awful" about it. I'm neutral about its UX - neither memorable nor despicable. It may be missed if the new app's UX turns out to be worse on whatever metrics you're using.

As they say in appendix 8:

> We create the synthetic data to reflect common time-series patterns using traditional statistical models. We start with four simple times series patterns:

> • Piece-wise linear trends (I), where the number of the piece-wise linear components is randomly chosen between 2 and 8.

> • ARMA(p, q) (II), where 1 ≤ p, q ≤ 8 and the corresponding coefficients are generated from either a multivariate Gaussian or a uniform, then normalized.

> • Seasonal patterns. In particular we create the sine (III) and the cosine (IV) waves of different random periods between 4 and max context length / 2 time-points and time delays.

If there were no such underlying patterns in the class of all time-series data, then even the idea of traditional time-series models would be fundamentally misplaced.

And since this is a transformer model, it also looks for patterns in the problem-specific input data at inference time, just like how the input context to an LLM influences its output's relevance.

I have a different take, centered around this idea: Not everyone was into thinking about everything all the time even before AI. I'd say most people most of the time outsourced actual thinking to someone else.

1) Reading non-fiction books:

Not all books, even the non-fiction ones, necessarily require any thinking by the reader. A book that narrates history, for example, requires much less thinking than something like "The Road to Reality" or "Godel Escher Bach."

Most of us outsourced the thinking and historical method to the authors of the history book and just passively consumed some facts or factoids. Some of us memorize and remember these factoids well, but that's not thinking, just knowledge storage.

Philosophically, what's the difference between consuming books this way and reading an LLM's output?

2) Reading research papers:

Most people don't read any research papers at all. No thinking there. Most people don't head to some forum to ask about latest research either. Also, researchers in most fields don't come out and do outreach regularly.

Indeed, an LLM may actually be the only pathway for a lot of people to get at least _some_ knowledge and awareness about latest research.

Those of us in scientific, engineering, humanities, healthcare fields may read some to many papers. But only a small subset reads very critically, looking for data errors, inconsistencies, etc. For most of us, the knowledge and techniques may be beyond our current understanding and possibly without any interest in understanding them in future either.

Most of us are just interested in the observations or conclusions or applications. Those may involve some thinking but also may not involve any thinking, just blind acceptance of the paper's claims and possible applications.

3) Coding:

Again, deep thinking is only done by a small set of programmers. Like the ones who write kernels, compilers, distributed algorithms, complex libraries.

But most are just passive consumers who read some examples online or ask stackoverflow or reddit for direct answers. Some even outsource all their coding entirely to gig sites. Not much thinking there except pricing and scheduling. What's the difference between that and asking an LLM or copying an LLM's answers? At least, the LLMs patiently explain their code, unlike salty SO users!

----

IMO, most people weren't doing much thinking even pre-AI.

Post-AI, it's true that some people who did do some thinking may reduce it.

But it's equally true that those people who weren't doing much thinking due to access or language barriers can actually start doing some thinking now with the help of AI.

- https://action.wemove.eu/sign/2026-01-omnibus-tech-petition-...

- https://action.wemove.eu/sign/2025-11-dpc-ireland-petition-E...

- https://action.wemove.eu/sign/2025-05-breakupbigtech-petitio...

- https://action.wemove.eu/sign/2025-01-elon-musk-dsa-petition...

- https://action.wemove.eu/sign/2024-12-Amazon-workers-petitio...

- https://action.wemove.eu/sign/2021-11-stop-big-tech-petition...