BRT has waxed poetic about AI as you, my loyal readers know. With this in mind, the smarter these entities get, the more deceitful they become as it seems cheating or hacking, as per us humans, is part of the equation becasue, after all, we created this tech, right?
The research suggests that the more sophisticated the AI model, the more likely it is to spontaneously try to “hack” the game in an attempt to beat its opponent. For example, it might run another copy of Stockfish to steal its moves, try to replace the chess engine with a much less proficient chess program, or overwrite the chess board to take control and delete its opponent’s pieces. Older, less powerful models such as GPT-4o would do this kind of thing only after explicit nudging from the team. The paper, which has not been peer-reviewed, has been published on arXiv.
Thru a glass Darkly
In order for AI to interact with the real world in real time, it requires software writing software, which means … We don’t know how AI works because human programmers cannot write code in real-time in any way, shape or fashion.
No comments:
Post a Comment