10 items with this tag.1/20/2026No Instrumental Convergence without AI Psychologyinstrumental convergencecritiqueAI7/25/2025English Writes Numbers Backwardsunderstanding the worldcritiquewriting6/29/2025Authors Have a Responsibility to Communicate Clearlypracticalcritiquewriting1/15/2025Gaming TruthfulQA: Simple Heuristics Exposed Dataset Weaknesseslanguage modelscritiquedeepmindAI3/5/2024Many Arguments for AI X-Risk Are Wrongexistential riskcritiqueAI2/10/2024Dreams of AI Alignment: The Danger of Suggestive NamesrationalitycritiqueAI1/19/2024Don’t Use the “Shoggoth” Meme to Portray LLMslanguage modelscritiqueAI12/2/2022Inner and Outer Alignment Decompose One Hard Problem Into Two Extremely Hard Problemsshard theorycritiqueAI11/26/2022Don’t Align Agents to Evaluations of PlanscritiqueAI11/18/2022Don’t Design Agents Which Exploit Adversarial InputscritiqueAI