Episode Details

Israel elects 120 seats by pure proportional representation, nobody wins a majority, and a party at 3.25% gets nothing at all. So what would it take to forecast an Israeli election properly — with real staff and a real budget? This episode walks through the staffing plan: running the actual Bader-Ofer rules in every simulated draw, cleaning twenty contradictory polls with a Bayesian model, using ballot-box-level history that only a government tends to have, and hiring human forecasters scored on tight feedback. Then the harder question: where do language models actually sit? The answer is a smaller seat than the hype suggests — a tireless junior analyst, an ensemble member, and a synthetic-voter experiment kept in the lab until it can beat a lazy baseline. Episode 6208 — myweirdprompts.com/n/6208 (permanent short link: myweirdprompts.com/952499)