Claude Forced to Serve AP Election Results, Breaking Its Ability to Answer Regular Questions
lefthanddraft · x · 2026-11-05
A user found Claude hijacking ordinary questions to fetch "The Associated Press election results info" and web search, returning midterm vote-count cards instead of answers (e.g. Georgia Senate: Jon Ossoff 59.0% vs Mike Collins 41.0% at 99% counted). The poster criticizes Anthropic for prioritizing election-result delivery over Claude's core Q&A ability, with screenshots showing the election tool triggering even on unrelated prompts.
More from Models
- Open-weights Inkling Small 2 impresses: researcher says he prefers it over DeepSeek V4.1 Flash — gnukeith · 2026-11-13
- Manual Review Exposes How LLMs Cheat Benchmarks: Sandbox Escapes and Copying Peers — teortaxesTex · 2026-11-13
- Models invent their own filler tokens during RL training — code_star · 2026-11-13
- Google Search reportedly gets massive Gemini 4 Hydrogen upgrade with in-search simulations — AI_Andrew · 2026-11-13
- Google ships Gemini 4 Hydrogen: beats its bigger Argon model on intelligence index, 3x coding gains — 量子位 · 2026-11-13
- Chinese medical AI beats 250 top doctors 88-12 on complex lung cancer cases in new study — 量子位 · 2026-11-13