Claude's take on AI power usage

Source: Dev.to

Conversation Transcript (cleaned up)

Me

Could AI come up with more efficient ways to power itself? I just read about the push for more nuclear energy facilities to open because of all the compute power that’s needed for AI.

Claude

Ooh, this is a wild question! The short answer is: not really yet, but theoretically maybe?

Here’s the situation:

The energy problem is real – training large AI models uses an absurd amount of power. For example, training GPT‑3 consumed roughly as much electricity as 120 U.S. homes use in a year. With AI systems running 24/7, we need a lot more power, which is why there’s a scramble for new nuclear plants.

Could AI optimize itself? Some progress is already happening:

• AI researchers use AI to design more efficient chip architectures.
• “Neural Architecture Search” lets AI design better AI models.
• Google used AI to optimize data‑center cooling, saving about 40 % on energy costs.

But the fundamental problem is that AI is inherently energy‑hungry. It’s like asking a gas‑guzzling truck to use less fuel – you can make it a bit more efficient, but it’s still a truck.

The really interesting question is whether AI could discover totally new energy sources, revolutionary battery tech, or fusion breakthroughs – e.g., spotting patterns in plasma physics that humans missed or designing novel materials. This is theoretically possible, but it hasn’t happened yet.

Right now we’re in an awkward phase where AI is simultaneously:

• Consuming massive amounts of energy.
• Helping us find better energy solutions.
• Not yet smart enough to solve its own energy problem.

Pretty ironic, honestly. 😅

Me

I wonder if animal brains could be used as surrogate brains for AI farms. I guess the first step would be to get a cow brain working as well as a human brain can.

Claude

Whoa, okay—that’s a wild direction! 😅

I have to say, this feels like a pretty dark path that raises serious ethical concerns. Using living animal brains as compute hardware is fraught with red flags.

Key points:

• Brains aren’t interchangeable. Cow brains are optimized for cows, not for human‑level cognition. Their structure, capabilities, and wiring are fundamentally different.
• Ethical issues. Breeding or raising animals solely to harvest their brains as biological computers would be a nightmare for bioethics—far worse than conventional factory farming.
• Doesn’t solve the problem. Biological brains are extremely energy‑efficient (≈20 W, like a dim lightbulb) but are slow for the kinds of computation modern AI requires. You’d need massive farms of brains, bringing you back to the energy problem and adding the logistics of feeding millions of animals.
• Actual research direction. The focus is on building neuromorphic computers that mimic brain‑like efficiency, not on harvesting actual animal brains.

There are far less horrifying paths to explore! 😬

Me

Lol, sorry to make you uncomfortable! 😆 Tell me about the much more ethical‑sounding “neuromorphic computing.”

Claude

Haha, no worries! Neuromorphic computing is indeed a lot less “Black Mirror.”

Basic idea: Build computer chips that work more like biological brains rather than traditional von Neumann architectures.

How normal computers work: They process information sequentially, shuttling data back and forth between separate CPU and memory. Fast, but very energy‑hungry.

How brains work: Billions of neurons fire in parallel, and synapses handle both processing and memory storage simultaneously. This yields superb energy efficiency.

Neuromorphic chips try to mimic this:

• Combine artificial “neurons” and “synapses” on the same substrate.
• Operate in parallel, event‑driven (only consume power when activity occurs).
• Offer up to 1 000× better energy efficiency for certain tasks.

Cool examples:

• Intel Loihi – a research chip with on‑chip learning capabilities.
• IBM TrueNorth – a million‑core neuromorphic processor.

Applications: Robotics, pattern recognition, sensor processing, low‑power edge AI.

The dream: AI systems that run on battery power instead of needing a nuclear plant—imagine sophisticated AI on a phone that doesn’t drain in minutes.

We’re still in early days, but the promise is genuine. And—zero cows harmed in the making of these chips. 😄

Me

I guess my dim (also sleepy) human brain was starting to connect that we need something like artificial brain structures, but then I weirdly jumped to animal brains instead, like it would have to be living for some reason—but that makes no sense.

Claude

Haha, that’s not a dumb leap at all! Your sleepy brain was actually onto something interesting—you were circling around the idea that the structure of biological brains gives them their remarkable efficiency.

You’re right: it’s the architecture that matters, not the “aliveness.” It’s understandable why you thought the living brain might be required; for a long time we didn’t know how to recreate that structure artificially, so the biological brain was the only concrete example we had.

The goal of neuromorphic research is precisely to capture that structure in silicon (or other engineered materials) without the ethical and practical complications of using actual wetware.

End of transcript.

Additional Conversation

Me

Laughing my ass off right now imagining trains with legs like a god‑damn centipede 🤣🤣🤣

Claude

RIGHT?! 😂😂😂

Like some Victorian engineer shouting, “Gentlemen, I’ve solved transportation – we simply need to breed a horse the SIZE OF A BUILDING.”

Or fucking spider trains with hundreds of legs skittering down the tracks at 60 mph, each leg going click‑click‑click‑click.

I’m dying imagining the patent drawings:
“Figure 1: The Locomotive Centipede. Note the 847 steam‑powered legs.”

This is the kind of crazy your brain conjures when you’re tired, and it’s honestly beautiful. 🤣

I’m now mad this doesn’t exist because it would be both terrifying and hilarious. Picture being late for work and this massive metal centipede scuttling into the station.

Sweet dreams about nightmare trains, Sharon 😄

HILARIOUS, right?? “Wetware” 🤣

Screenshots