{"source":"manifold","id":"EL0tZDuqnjE1jhFnzjp5","ticker":null,"slug":"at-the-beginning-of-2028-will-llms","title":"At the beginning of 2028, will LLMs still make egregious common-sensical errors?","description":"A duplicate of @/ScottAlexander/in-2028-will-gary-marcus-still-be-a, with the ban on \"bizarre hacking like tricks\" removed and clearer resolution criteria.\n\nThis market resolves based on the behavior of all leading chatbots at the beginning of 2028. (Only ones that can actually be tested.)\n\nResolves YES if people can find three extremely obvious questions, that an average human teenager could certainly answer, which any leading chatbot still fails at at least half the time when asked.\n\nOnly the LLM portion of the chatbot is being tested here. Image-recognition and generation capabilities are not.","image":"https://storage.googleapis.com/mantic-markets.appspot.com/contract-images/IsaacKing%2F2ab8ed18e097.jpg","icon":null,"active":true,"closed":false,"start_date":"2024-01-15T20:46:00.135000Z","end_date":"2028-01-01T07:59:00Z","closed_time":null,"volume":10009.464008448002,"volume_24hr":0.0,"volume_24h_change":null,"normalized_vol_24hr":null,"normalized_volume":31.8520565032959,"liquidity":1000.0,"open_interest":0.0,"categories":["Science and Technology"],"tags":[],"synthetic":true,"is_group":false,"group_key":null,"parent_event_id":null,"probability":0.647839,"spread":null,"top_outcome":"At the beginning of 2028, will LLMs still make egregious common-sensical errors?","top_outcome_probability":0.647839,"top_outcome_prob_24h_change":0.0,"top_outcome_volume_24h_change":0.0,"updated_at":"2026-06-03T06:46:47.573580Z","fetched_at":"2026-06-03T06:46:47.573580Z","added_at":null,"url":"https://manifold.markets/IsaacKing/at-the-beginning-of-2028-will-llms","chart_24h":[0.647839,0.647839],"markets":[{"source":"manifold","id":"EL0tZDuqnjE1jhFnzjp5","event_id":"EL0tZDuqnjE1jhFnzjp5","slug":"at-the-beginning-of-2028-will-llms","question":"At the beginning of 2028, will LLMs still make egregious common-sensical errors?","group_item_title":null,"description":"A duplicate of @/ScottAlexander/in-2028-will-gary-marcus-still-be-a, with the ban on \"bizarre hacking like tricks\" removed and clearer resolution criteria.\n\nThis market resolves based on the behavior of all leading chatbots at the beginning of 2028. (Only ones that can actually be tested.)\n\nResolves YES if people can find three extremely obvious questions, that an average human teenager could certainly answer, which any leading chatbot still fails at at least half the time when asked.\n\nOnly the LLM portion of the chatbot is being tested here. Image-recognition and generation capabilities are not.","image":"https://storage.googleapis.com/mantic-markets.appspot.com/contract-images/IsaacKing%2F2ab8ed18e097.jpg","icon":null,"outcomes":["YES","NO"],"outcome_prices":[0.647839,0.352161],"probability":0.647839,"spread":null,"active":true,"closed":false,"start_date":"2024-01-15T20:46:00.135000Z","end_date":"2028-01-01T07:59:00Z","closed_time":null,"volume":10009.464008448002,"volume_24hr":0.0,"prob_24h_change":0.0,"volume_24h_change":0.0,"normalized_vol_24hr":null,"normalized_volume":31.8520565032959,"liquidity":1000.0,"categories":["Science and Technology"],"countries":[],"updated_at":"2026-06-10T03:37:20.483894Z","fetched_at":"2026-05-05T13:29:58.281893Z","added_at":null,"url":"https://manifold.markets/IsaacKing/at-the-beginning-of-2028-will-llms","event_title":"At the beginning of 2028, will LLMs still make egregious common-sensical errors?","chart_24h":[0.647839,0.647839]}],"_meta":{"attribution":"pdata.world — aggregated prediction-market data across 8 platforms","canonical_url":"https://pdata.world/events/manifold/EL0tZDuqnjE1jhFnzjp5","as_of":"2026-06-10T14:51:54.293821Z","docs":"https://api.pdata.world/docs","cite_as":"According to pdata.world (tracking Manifold): \"At the beginning of 2028, will LLMs still make egregious common-sensical errors?\" — top market at 65% probability across 1 outcome","source_url":null}}