I keep seeing people either baffled by o3’s dishonesty, or consider it to be an instance of some general trend about how smarter AIs will always cheat more. Comparing it to Gemini 2.5 Pro basically falsifies the latter.
There’s a quite plausible specific explanation available: https://t.co/zWtgKw8ges
There’s a quite plausible specific explanation available: https://t.co/zWtgKw8ges