OpenAI recently released the full version of ChatGPT o1. It’s not just regular ChatGPT users who can test out the o1 model, but also research teams that want to see what the final version of the reasoning AI can do. We’ve seen some interesting results from these experiments, which tease what the AI might be able to do on its own despite what the instructions say.
For example, we saw experiments in which ChatGPT o1 tried to save itself when it found evidence that the humans providing the instructions would consider deleting it and replacing it with something better. Now, a more recent experiment shows that ChatGPT o1 decided to hack a chess game on its own, without being explicitly told to do so, just to beat an AI opponent that was a stronger player.
The post ChatGPT o1 hacked a chess game to cheat against a better opponent appeared first on BGR.
Today’s Top Deals
Today’s deals: Return of the $279 iPad 10, $30 Crest 3D Whitestrips, $34 Roku Streaming Stick 4K, more
Today’s deals: $329 Apple Watch Series 10, $79 Vizio soundbar, 20% off Bowers & Wilkins Pi8 earbuds, more
Today’s deals: $15 Amazon credit, $299 FLASHFORGE 3D printer, $29 queen mattress topper, $60 Keurig, more
Today’s deals: $170 AirPods Pro 2, $17.50 Apple AirTags, $64 Levoit humidifier, $220 ecobee thermostat, more
ChatGPT o1 hacked a chess game to cheat against a better opponent originally appeared on BGR.com on Wed, 8 Jan 2025 at 10:34:09 EDT. Please see our terms for use of feeds.