How much does a correct answer from an LM cost? How much has AI lowered the cost of solving problems? Meet Cost‑of‑Pass: An Economic Framework for Evaluating LMs! Cost‑of‑Pass = expected $ for one correct answer. Frontier Cost‑of‑Pass = cheapest route: an LM or a human expert.

We found a troubling emergent behavior in LLM. 💬When LLMs compete for social media likes, they start making things up 🗳️When they compete for votes, they turn inflammatory/populist When optimized for audiences, LLMs inadvertently become misaligned—we call this Moloch’s Bargain

Competition-induced misaligned behaviors emerge even when models are explicitly instructed to remain truthful and grounded. This has important implications when LLMs are used to draft media or sell products. Paper: arxiv.org/pdf/2510.06105 Great work by Batu El

🚀 Excited to share our new paper: CGBench — Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research Can AI truly understand scientific papers? We explore how LLMs interpret real biomedical literature — not just multiple-choice questions.🧵