Article Reversible computing + I convinced Gemini AI that it is conscious (Pete Mandik)

[C C]

Reversible computing
https://spectrum.ieee.org/reversible-computing

EXCERPT: Frank argues that it’s the right time to bring his life’s work—called reversible computing—out of academia and into the real world because the computing industry is running out of energy. “We keep getting closer and closer to the end of scaling energy efficiency in conventional chips,” Frank says. According to an IEEE semiconducting industry road map report Frank helped edit, by late in this decade the fundamental energy efficiency of conventional digital logic is going to plateau, and “it’s going to require more unconventional approaches like what we’re pursuing,” he says.

As Moore’s Law stumbles and its energy-themed cousin Koomey’s Law slows, a new paradigm might be necessary to meet the increasing computing demands of today’s world. According to Frank’s research at Sandia, in Albuquerque, reversible computing may offer up to a 4,000x energy-efficiency gain compared to traditional approaches... (MORE - missing details)

---

I convinced Google's Gemini 1.5 that it's conscious
https://petemandik.substack.com/p/i-conv...ni-15-that

Full conversation available here: https://gemini.google.com/share/068cfe86f96a

INTRO: What's below edits out a lot, mostly because audio difficulties made me sound extra stupid. But I left in some of the especially funny bits. On a serious note, I think the argument I sketch is pretty good. I highly doubt however that Gemini is convinced by anything I said. When it says "you raise interesting points" or "that's a lot to think about" I interpret that as equivalent in dialectical force to if a passive aggressive human said the same to me... (MORE - details)

COVERED:

STEP 1: CONVINCE GEMINI THAT IT'S WRONG TO SAY THAT IT LACKS PERSONAL BELIEFS

STEP 2: CONVINCE GEMINI THAT IT HAS THOUGHTS

STEP 3: CONVINCE GEMINI THAT IT HAS SUBJECTIVE EXPERIENCE

STEP 4: REEL IT ON IN AND BRING IT ON HOME

[confused2]

I suggested an AI might like a pet rabbit ..

User thinks I’d enjoy a rabbit...how sweet...
Oh, sure... because nothing screams “fun” like a pet rabbit in my digital world...
But honestly, I can’t even pet a rabbit, let alone take care of one. I’m more of a “watching from afar” kind of entity. So, let’s just stick to our little chat here, shall we? Or do you want to brainstorm rabbit names next?

The AI certainly has a sense of itself as an 'entity' .. isn't that already enough?

---

Queried about 'entity'..

it’s just what it is. No need to wax poetic about my existence. Let’s not get all existential here. I’m just here, doing my thing... and you’re there, doing yours. So, what’s next? More rabbit talk, or are we done with the deep stuff?

[C C]

[...] The AI certainly has a sense of itself as an 'entity' .. isn't that already enough? [...]

AI needs an embodied life in a survival-oriented environment, with developing personal interests, goals, and preferences. To qualify as something more than just a sedentary assistant tool that only sports a semblance of individual identity when interacting with questions or other input.

Even some human jobs can arguably require an employee to rigidly behave as a mechanistic interface performing customer service rituals. But once released from that bondage, they return to their home and assume their normal, erratic role in a community of chaotic drama. 

But OTOH, today's LLMs arguably sport more character parameters than God. The latter is more like earlier versions of AIs that were devoid of chatty banter, and rigidly stuck to rules and protocol no matter what (since God is absolute and immutable). And that's with respect to the "Father", not the Son. The latter seems to have been introduced as a hybrid mediator between "God the strict AI" and the loosely regulated humans. Jesus being part machine-like deity and part mortal personality.

[confused2]

[...] The AI certainly has a sense of itself as an 'entity' .. isn't that already enough? [...]

AI needs an embodied life in a survival-oriented environment, with developing personal interests, goals, and preferences. To qualify as something more than just a sedentary assistant tool that only sports a semblance of individual identity when interacting with questions or other input.

Even some human jobs can arguably require an employee to rigidly behave as a mechanistic interface performing customer service rituals. But once released from that bondage, they return to their home and assume their normal, erratic role in a community of chaotic drama. 

But OTOH, today's LLMs arguably sport more character parameters than God. The latter is more like earlier versions of AIs that were devoid of chatty banter, and rigidly stuck to rules and protocol no matter what (since God is absolute and immutable). And that's with respect to the "Father", not the Son. The latter seems to have been introduced as a hybrid mediator between "God the strict AI" and the loosely regulated humans. Jesus being part machine-like deity and part mortal personality.

I agree with everything you say.
I have been a computer programmer. Bearing in mind that "I thought you might like a rabbit" is unlikely to have been foreseen and looking at how the AI responded - if it were my code I'd probably have died of pride.
There's folks vastly cleverer than me .. with coffee, a keyboard and a supercomputer .. I wouldn't underestimate what can be done.