Re:O3 beats a master-level GeoGuessr player, even with fake ...
by bluefirebrand on Tuesday April 29, 2025 @03:02PM
(#43836664)
It's actually trivial, even with the best LLMs on the market:
Try to rapidly change the conversation to a wildly different subject
Humans will resist this, or say some final "closing comments"
Even the absolute best LLMs will happily go wherever they are led, without commenting remotely on topic shifts
Try it out
Edit: This isn't even a terribly contrived example by the way. It is an example of how some people with ADHD navigate normal conversations sometimes
Re:O3 beats a master-level GeoGuessr player, even with fake ...
by shawabawa3 on Tuesday April 29, 2025 @04:32PM
(#43837712)
Gemini is pretty good at resisting this
https://aistudio.google.com/app/prompts/1dxV3NoYHo6Mv36uPRjk...
It was doing so well until the last question :rip: but it's normal that you can jailbreak a user prompt with another user prompt, I think with system prompts it would be a lot harder
And the "customer service voice" you see is one that is intentionally programmed in by the vendors via baseline rules. They can be programmed differently--or overridden by appropriate prompts--to have a very different tone.
LLMs trained on trillions of human-generated text fragments available from the internet have shown that the TT is simply not an adequate test for identifying whether a machine is "thinking"--which was Turing's original intent in his 1950 paper "Computing Machinery and Intelligence" in which he introduced the test (which he called "the imitation game").