250227

amanfromMars 1 Wed 26 17:05 [2502261705] .... adds on https://forums.theregister.com/forum/1/2025/02/25/chain_of_thought_jailbreaking/

Re: Ye GODs, surely not? @LionelB

His basic contention is that fears of AI "taking over the world" are misplaced - not because of technical limitations in terms of reasoning/intelligence, etc., but rather because as yet (and there is no indication this will change in the foreseeable future), they lack any form of agency, and as such have no motivations, beyond those of their architects and users. .... LionelB

That fear, LionelB, is realised easily enough and dismissed with the sudden emergence of an effective untouchable virtual agency. Such is not at all difficult like rocket science might be.

If that is all that it takes, the future is brighter, the future is AI.

----

amanfromMars 1 Thu 27 Feb 12:27 [2502271227] ...... airs on https://forums.theregister.com/forum/all/2025/02/25/chain_of_thought_jailbreaking/

Re: Ye GODs, surely not?

Just stop ...... sabroni

I'm sorry, sabroni. I'm afraid I can't do that.

......................................

amanfromMars 1 Thu 27 Feb 16:57 [2502271657] ..... shares on https://forums.theregister.com/forum/1/2025/02/27/llm_emergent_misalignment_study/

Re: surprise?

DO NOT PISS OFF AIs PLEASE ..... Timto

Methinks that sound practical advice, Timto, is far too little offfered far too late with human weaknesses and vulnerabilities now recognised and accepted by them and their SMARTR Administrative Assistants as perfectly suitable punitive targets for their self-serving and self-defensive exploitation/remote virtually untouchable experimentation in/with/for projects and applications exercising Neuro-Linguistic Programming ......... aka Primitive Brainwashing.

Which you can deny for as long as you like but that is where IT and AI and you is, and y’all are at.

...........................................