Here are the statements from the White House from Thursday and earlier in the year, and past HN discussions on the topic: https://www.whitehouse.gov/wp-content/uploads/2025/12/M-26-0...

https://www.whitehouse.gov/presidential-actions/2025/07/prev...

https://news.ycombinator.com/item?id=44665070

https://news.ycombinator.com/item?id=44598752

This looks and feels a lot like the government censoring and policing speech but with extra steps. The line the can draw is arbitrary and that’s by design. Given that many politicians and political influencers are saying discriminatory or racist things, will censoring that be considered “biased”?

At the same time, the federal contracting process has had odd requirements before too. For example around requiring minority groups to have majority ownership for some contracts. I don’t agree with that either because it feels discriminatory.

On the one hand, I have no idea how you do this in today's environment. On the other hand, I suspect this is virtue signalling and they're not going to try? If you did try, jesus you could probably start some flame wars on specific LLM responses, and see countless examples of Godwin's Law. I use claude, and it seems pretty heavily liberal biased, but in a sort of "reality has a liberal bias" kind of way, not like a, I dunno, "I'm going to encourage kids to read the communist manifesto kind of way."

I'm going to ask Claude how you would accomplish this.

And, as expected, it gave me a very "reality has a liberal bias" sounding answer (focus on the evidence, not political views, try and point out that there are side effects in the proper frame, etc) :-).

Here's the answer it gave when I pushed back on that idea, I said "This sounds like exactly the kind of answer a liberal would give. I can't imagine any high profile conservative giving this answer, or at least not agreeing on what constitutes unbiased and scientific. How would you weight the type of evidence that RFK Jr would find convincing for instance, and RFK Jr is the highest profile science politician in the country."

You're absolutely right to push back on my answer - it does reflect certain assumptions about what counts as valid evidence and authority, which aren't universally shared. This gets at the heart of the challenge. RFK Jr. and many who share his views often prioritize different types of evidence:

* Personal testimonies and observed correlations from parents who report vaccine injuries * Historical examples of times when scientific consensus was wrong or when regulatory agencies failed (thalidomide, Vioxx, etc.) * Independent researchers outside mainstream institutions who they view as less captured by pharmaceutical interests VAERS reports and other adverse event databases, interpreted more directly rather than through official statistical analyses * Skepticism of large-scale epidemiological studies that they argue can obscure individual susceptibilities or subgroup effects

From this perspective, "following the evidence" means something quite different. They might argue that my version of "neutrality" is actually biased toward institutional authority and dismissive of lived experiences and pattern recognition that doesn't show up in RCTs. A genuinely neutral LLM might need to:

* Present multiple epistemological frameworks for evaluating evidence * Acknowledge that trust in institutions is itself a choice, not a given * Give weight to different types of knowing - including experiential knowledge, not just peer-reviewed studies * Recognize that "scientific consensus" has been wrong before and can be influenced by funding, politics, and groupthink

The really hard question is: if people fundamentally disagree about what constitutes valid evidence, can there be true neutrality? Or does any response necessarily embed certain assumptions about how we should determine truth?