🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

All decisions are made under uncertainty. Almost no decisions can be reduced to gambling. argmin.net/p/all-bets-are…

Demos play an outsized role in the complex world of artificial intelligence evaluation. Maybe that's not a bad thing. argmin.net/p/demo-or-die

It turns out to be hard to evaluate natural language with natural language. What should we take away from the conundrum of LLM evaluation? argmin.net/p/evaluation-o…

What if instead of The Terminator and The Matrix, we used Severance and South Park to think about AI? argmin.net/p/maybe-just-b…

Reading Marion Courtade and Kieran Healy's *The Ordinal Society* as a broader critique of quantitative social science. argmin.net/p/pretending-n…

Rossi’s Metallic Rules and why it’s hard to measure benefit when evaluating social programs. argmin.net/p/rossis-metal…

A syllabus for a course on machine learning evaluation. argmin.net/p/machine-lear…

Guest post! Deb Raji.bsky.social reflects on our machine learning evaluation class (and the chaos of co-teaching with me). argmin.net/p/to-measure-i…

Neil Postman’s Moral Theology and the power of stories about correlations. argmin.net/p/correlations…

Digging into the very political history of academic computer science. argmin.net/p/computer-sci…

On the cultivation of a "pure" computer science and why we should reject this concept. argmin.net/p/computationa…

George Forsythe's 1962 vision for computer science education. argmin.net/p/physics-for-…

Louis Fein’s utopian vision of academic computer science was delightfully boring. argmin.net/p/may-you-live…

I weigh in on the Trump administration’s newfound obsession with Gold Standard Science and reproducibility. Though it’s not all in bad faith, it’s likely to backfire. argmin.net/p/this-is-fine

Who should get to define which science is "good" and "bad"? argmin.net/p/the-good-the…

I wrote a defense of peer review, as it will be the system academia uses to reinvent itself. argmin.net/p/a-defense-of…

I use the vetting of papers as a case study for how academic process evolves. argmin.net/p/the-open-mar…

p-values supposedly measure the correlation between interventions and outcomes. But what happens when a measure becomes a target? argmin.net/p/milton-fried…

Validity as a style guide for science. argmin.net/p/strunk-and-w…

In a new paper, Juanky Perdomo and I ask when forecasting and prediction can be solved by sneaky accounting. The answer turns out to be “more often than you’d expect." argmin.net/p/in-defense-o…