It is truly fascinating, I wonder how it evolved like that.
Before becoming a spring as it is today how was it hunting in the past? What constraints made it need such a mechanism instead of a typical web?
Animals (humans included) work on the same "framework" (i.e., the brain), so even if the definition of consciousness is fuzzy, we can rank them in a more or less consistent way. LLMs, on the other hand, are just the linguistic part of a brain without anything else. Whether this is enough to be conscious is up for debate (in my opinion no, but that's irrelevant), but it falls outside the spectrum assumption IMO.
> we'll have figured out a renewable energy concept that'll handle the load by then"
Seems like wishful thinking. If anything with the current electrical trends there will be even more demand for energy in the future and unless some miracolous clean energy source is invented, nuclear (or fossil fuel) will need to be used
I've seen a few studies about it. If i remeber correctly, basically making them talk like a caveman increases the information density of every token and decreases the chance that they would allucinate.
As sources this is the one i found but i'm sure there are others:
> Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models
> Text Compression as a Proxy for LLM Reasoning Efficiency
> Id pay to be able to reliably set LLMs to this mode,
You can do it for free. Just give it instrucitons to avoid emotional tones and flattery and it will sound a lot more robotic.
If you look into other examples I'm sure you will find other good instructions based on your need
> They talk like real people. They use a relaxed and friendly tone. They often praise you, and when they “push back” they’re gentle and attentive.
> Maybe I would prefer a more radical solution: drop the human pretense entirely. Make the agent sound clinical, robotic.
Honestly this problem is easy to solve when you gave them the right instructions. It stops being a "relationship" and stars being a tool (for some examples see the smart caveman (my favorite) or just something simple like "Responses should be factual and direct, avoid emotional overtones" or "Avoid flattery of any kind")