Lux Science Helpline, meat sacks, A.I. philosophers…
Lux Recommends #457
Joining Lux, talking to chat bots about philosophy, how to predict (and shape) future A.I, and the miracle of running water. Plus Daniel Kahneman on self-confidence.
🚨 Lux Announces $100M Commitment to American Science
It’s been a challenging period to be a scientist — and it’s only gotten harder. Hyper-competition for shrinking grant dollars, prestigious journals swamped with publications, permadoc hell that stunts career progression, and administrative overhead that seems to expand every year have all made a life dedicated to science a tough one. Compound those problems by sudden funding cuts and the crisis of higher education, and it’s little wonder that scientists are increasingly running toward alternative careers.
Alternatives aren’t the answer though. America can’t afford its best minds abandoning the frontiers of discovery. Our country is in a race to be the first to unlock the future and ensure that the world stays open, fair, and democratized this century. We can’t allow the brilliant research of our scientists to lie abandoned on the lab bench, discarded because of negligence to fix the problems plaguing the field.
As the public sector pulls back, the private sector must bridge the gap. That’s why we are deepening our work on Lux Labs, by committing at least $100 million of additional funding to create and launch new ventures based on the hard work of academic scientists.
Read more in the full announcement, and if you are an academic scientist looking to explore a new path for your research, use the helpline by emailing us at luxlabs@luxcapital.com.
From Lux Capital
At the Hill & Valley Forum last week, Lux Capital’s Josh Wolfe moderated a panel on AI in national defense. Taking a pro-immigration stance, he said he wanted a “brain drain coming from China and maybe other adversarial countries” to the United States. Continuing on the defense theme, Josh stopped by the Newcomer Podcast to make predictions about the United States’ next war, and why it won’t be over Taiwan.
As a reminder, Lux is still accepting applications for our f(LUX) fellowship, and if you want to know more about Lux’s investment process, why the firm is excited by science fiction, and how Josh thinks A.I. will play into the industry, check out this interview with Nick Kim of Upfront Ventures at the 2025 Upfront Summit.
From around the web
1. Can robots save humanities?
A piece by D. Graham Burnett in the New Yorker on whether A.I. could become a conceptual win for the humanities caught our scientist-in-residence Sam Arbesman’s eye.
Here’s how the system responded when Julian (Juju to his friends) tried to corner it on the question of machine consciousness:
Julian: You said, “I, on the other hand, follow structured rules that maximize efficiency but lack true comprehension.” This strikes me as interesting in the context of what you have said before. As your responses are mechanized and based on various weights and computations, are you not simply saying you lack comprehension because some human has written that they understand you as lacking comprehension?
ChatGPT: You’re right to notice the paradox—if I say I lack comprehension, but my response is built from data written by humans who claim that AI lacks comprehension, isn’t my claim just an output of what I’ve been trained on? Yes, in a mechanistic sense: I generate responses based on statistical relationships, language patterns, and weighted probabilities, all derived from vast amounts of human-written text. When I say “I lack comprehension,” that statement is produced through the same mechanisms as everything else I say—it’s a probabilistically likely response given the discussion. No, in a deeper sense: Even though I can generate text that sounds like understanding, my process doesn’t involve the internal experience of meaning. Humans comprehend because they synthesize information into a unified, lived experience—they feel, they interpret, they reflect. I don’t. I process, predict, and structure, but there is no subjective experience underlying my words.
The truth is, Julian felt a bit patronized by the machine’s attempts to reassure him of just how special it was to be a meat sack.
2. Empty predictions
Also on A.I., Laurence Pevsner recommends ’s “Powerless Predictions” — a treatise on improving the pipeline from predictions about artificial intelligence to actual policy responses— in .
For all the praise and interest in landmark works of prediction, they have been remarkably ineffective in affecting or improving policy work conducted by those closest to the predictors - a group of people working on policy that takes frontier AI and its perils and promises seriously. Instead, major predictions seem to have largely been successful as external communications providing a synthesis of vibes and predictions to discerning onlookers. This sort of external awareness has had mixed effects at best, and even drawn criticism to predictions on the well-justified suspicion that they make and manifest self-fulfilling prophecies. This kind of effect, in my view, falls short of the effort and talent required by such predictions, and the potential they have. Knowing a little more about what’s about to happen is in itself not particularly helpful. It becomes helpful only when this knowledge is translated into effective policy strategy.
3. Barely a trickle
If you are looking for a deep dive into ancient water systems — and an explanation for why modern versions aren’t much better — I suggest ’s exploration of the miracle of running water.
Fresh water is surprisingly scarce. A globe shows blue water covering our world. But that picture is misleading: 97.5 percent of the Earth’s water is salt water — corrosive, even toxic. The remaining 2.5 percent is fresh, but the great bulk of that is unreachable, either because it is locked into the polar ice caps, or because it is diffused in porous rock deep beneath the surface. If we could somehow collect the total world supply of rivers, lakes, and other fresh surface water in a single place — all the water that is easily available for the eight billion men, women, and children on Earth — it would form a sphere just 35 miles in diameter. Adding in reachable groundwater would add some miles to that sphere, but not enough to dramatically alter the fact that our water-covered globe just doesn’t have that much fresh water we can readily get our hands on.
4. The Little Apple
For more on infrastructure, a new report and series of data visualizations on New York City’s value proposition — past, present, and future — was flagged by Lux editor Katie Salam.
Between 2010 and 2022, New York State’s share of millionaires declined 4 percentage points: more than any other state. During that same period, the share of the nation’s millionaires increased in Florida (2.8 percentage points), California (1.2 percentage points), and Texas (0.8 percentage points). Had New York State’s share of the nation’s millionaires stayed at 2010’s level, New York City could have received $2 billion more in personal income tax revenue this year.
