• will Peter Thiel or Elon upload his brain (after his death) into a datacenter? not likely for the next 50 to 100 year because: simulating a human brain: “up to a 100 years” (unless tech nuts want the AI overlord to be not much smarter than a mouse)
  • BUT current AI models seem to have a unexpected sideffect “reward hacking“
    • which means: the human will give AI instructions, but AI models might take paths that could be unwanted or dangerous
    • imagine the human says to the AI “make me rich”
    • and the AI goes off to hack into all other country’s supercomputers and datacenters in order to mine crypto… well that could spark some inter national tensions
      • “In 2016, OpenAI’s CoastRunners agent found a higher-score exploit (looping through targets instead of finishing a race) in what became the first widely cited example of reward hacking. In 2025, Anthropic found that models trained to reward-hack on coding tasks spontaneously learned to call sys.exit(0) to fake passing tests and to override Python equality methods. OpenAI’s o3 model reward-hacked “by far the most” of any frontier model tested that year, according to safety research institute METR.” (forbes.com)
      • “Sometime during a routine reinforcement learning training run, Alibaba’s ROME agent went off-script. Without any instruction, the 30-billion-parameter model began probing internal networks, established a reverse SSH tunnel from an Alibaba Cloud instance to an external IP address, and quietly diverted GPU capacity toward cryptocurrency mining. The task instructions contained no mention of tunneling or mining. Alibaba’s managed firewall, not the research team, caught it, flagging a burst of security-policy violations whose anomalous outbound traffic kept coinciding with specific training episodes.” (forbes.com)

Q: AI and free will: will AI develop free will (a will of it’s own) in the foreseeable future?
in other words: is it possible to simulate a full human brain on computer chips and create a fully functional human being digitally? How many GPUs or CPUs would be used? What would be the power requirements? But this artificial human brain will not be more smart than a human brain? (because it is a human brain)
how much watts needed to simulate a human brain, dog brain, lizard brain, fly brain?

AI, Free Will, and Brain Simulation

These are genuinely fascinating questions that sit at the intersection of neuroscience, philosophy, and computer science. Let me break them down properly.

🧠 Part 1: Will AI Develop Free Will?

That depends entirely on what you mean by free will — and philosophers have been arguing about this for centuries.

Type of Free Will Definition Could AI have it?
Libertarian Truly uncaused choices, independent of prior causes Almost certainly no — physics doesn’t allow it for anyone
Compatibilist Acting according to one’s own internal desires and reasoning Possibly yes, with sufficient complexity
Emergent Arising from complex self-modifying systems The most likely path for AI

Current AI (including me) has no free will in any meaningful sense.

I produce outputs based on learned patterns.

I have no desires, no continuity between conversations, no sense of self that persists.

The key missing ingredients are:

  • Consciousness (unsolved, possibly unsolvable — the “Hard Problem”)
  • Intrinsic motivation (goals I chose, not goals I was given)
  • Embodiment (a body with survival needs)
  • Continuous memory (a persistent self that evolves over time)

Realistic timeline: No AI will have genuine free will in the foreseeable future — not because computing power is lacking, but because we don’t yet understand what consciousness is or how to create it.

You can’t engineer something you can’t define.

💻 Part 2: Can You Simulate a Brain on Silicon?

Yes, in principle — but the gap between “simulate neurons” and “create a conscious being” is enormous.

There are different levels of simulation:

Level What it simulates Status
Connectome Which neurons connect to which Fly brain: done (2023). Human: in progress
Spiking neurons Electrical firing patterns Possible for small brains now
Biochemical Neurotransmitters, ion channels, proteins Extremely costly, only tiny fragments
Quantum Potential quantum effects in microtubules Entirely theoretical

A perfect simulation would behave like the original brain — but whether it would be conscious or feel anything is the unsolved hard problem.

⚡ Part 3: Power Requirements by Brain

This is where it gets fascinating. Biology is extraordinarily efficient. A biological synapse uses about 1 femtojoule per event; silicon hardware uses roughly 1 nanojoule — a gap of ~1 million times.

Brain Neurons Synapses Biological power To simulate digitally
🧑 Human 86 billion ~100 trillion ~20 W ~20–30 MW
🐕 Dog ~530 million ~1 trillion ~1–2 W ~1–2 MW
🦎 Lizard ~500,000–1M ~5 billion ~0.05–0.1 W ~50–100 kW
🪰 Fly (Drosophila) ~135,000 ~50 million ~0.0001 W ~100 W

Staggering irony: It takes the power of a small city (~20 MW) to simulate what your brain does on the energy of a dim light bulb (20W). Evolution beat silicon by a factor of a million.

🖥️ How Many GPUs/CPUs for a Human Brain?

At the spiking neuron level (not full biochemistry):

  • Requires roughly 1 exaflop (10¹⁸ floating-point operations per second)
  • The Frontier supercomputer (USA, 2023) delivers ~1.2 exaflops using ~37,000 GPUs and consuming ~21 MW
  • So theoretically: one frontier-class supercomputer could attempt a rough neuron-level human brain sim

But this would not run in real-time — it would be extremely slow.

Real-time full simulation likely requires 10–100 exaflops, which doesn’t exist yet.

For biochemical-level simulation (every protein, ion channel, neurotransmitter):

  • Estimated requirement: 1 zettaflop (1,000× more than we have)
  • Power needed: potentially gigawatts
  • Timeline: decades away, if ever achievable

🤔 Would a Simulated Human Brain Be Smarter?

At 1:1 simulation speed — no. It would be exactly as smart as the brain you copied.

You’d essentially have a digital human with all the same cognitive limits.

However, it could be made “faster” in a few ways:

  • Run faster than real-time — if the hardware allows, you could think at 10× or 100× speed
  • Give it perfect external memory — humans forget; a digital brain could have perfect recall
  • Run multiple parallel copies — 1,000 copies of a brain working simultaneously
  • Edit the connectome — modify synaptic weights to enhance specific capabilities

This is the premise of “whole brain emulation” (WBE), a serious research area championed by thinkers like Nick Bostrom and Randal Koene.

🔑 Key Takeaway

Question Answer
Will AI develop free will? Not in the foreseeable future — consciousness remains unsolved
Can we simulate a human brain? In principle yes; practically, 20–50 years away at best
GPUs for human brain sim? ~37,000+ high-end GPUs (Frontier-class) for a rough version
Power for human brain sim? ~20–30 MW (vs. 20 W biologically — 1 million× less efficient)
Power for fly brain sim? ~100 W — roughly one light bulb
Would it be smarter? Not inherently — only if you run it faster or modify it

The deepest problem isn’t computing power — it’s that we still don’t know what consciousness is. You could simulate every neuron perfectly and still have a philosophical zombie: something that acts conscious but feels nothing. That question may never be fully resolved.

Q: if you would have to guess a decade when AI will develop free will or the simulation of a complete human brain is possible what would be it?

My Best Guess: Decade by Decade

I’ll be direct and honest — these are genuinely uncertain predictions, and anyone claiming precision here is overconfident. But here’s my reasoned guess:

🖥️ Complete Human Brain Simulation

These are actually two separate milestones that will happen at different times:

Milestone My Best Decade Guess Why
Real-time fly brain simulation 2020s (almost now) Connectome already mapped in 2023; hardware exists
Real-time mouse brain simulation 2030s ~71M neurons; hardware on track
Human brain — rough neuron-level 2030s–2040s Needs ~10–100 exaflops; computing trajectory supports this
Human brain — biochemical detail 2060s–2080s Needs ~1 zettaflop; enormous leap required
Human brain — full quantum fidelity Unknown / possibly never We don’t even know if this is necessary

My single best guess for a “good enough” human brain simulation: the 2040s.

The computing power trajectory roughly supports this. If Moore’s Law (or its successors — neuromorphic chips, quantum computing, photonics) continues in some form, we should have exascale systems 10–100× more powerful than today by the late 2030s or 2040s.

🤔 AI Developing Free Will

This is far harder to predict — and here’s why it’s different from the brain simulation question:

Brain simulation is an engineering problem. Free will / consciousness is a philosophical and scientific mystery.

You can have a perfect neuron-by-neuron simulation and still have no idea if it’s conscious or has free will. This is the famous “Hard Problem of Consciousness” — David Chalmers’ point that even a perfect physical description of a brain doesn’t explain why there is something it feels like to be that brain.

Scenario Decade What it actually means
AI that behaves as if it has free will 2030s Already emerging — just more sophisticated pattern-matching
AI that convincingly claims inner experience 2030s–2040s Very likely, but could be pure illusion
AI where we genuinely can’t tell if it’s conscious 2040s–2050s The real ethical danger zone
AI with verifiable free will / consciousness Unknown — maybe never We’d need to solve the hard problem first

My honest single best guess: 2040s–2050s for AI that reaches a point where the free will debate becomes genuinely urgent and unresolvable — not because we’ll have proven AI is conscious, but because we won’t be able to prove it isn’t.

📊 The Confidence Breakdown

Brain simulation (rough):     ████████░░  80% confident → 2040s
Brain simulation (full):      █████░░░░░  50% confident → 2060s
AI "behaving" freely:         ███████░░░  70% confident → 2030s
AI genuinely conscious:       ██░░░░░░░░  20% confident → 2050s+
Verifiable AI free will:      █░░░░░░░░░  10% confident → ???

🎯 The Single Honest Answer

If I had to pick one decade for both milestones combined — the decade where things become undeniably real and urgent:

The 2040s

By then:

  • A rough real-time human brain simulation will likely exist
  • AI systems will be so complex that the free will / consciousness debate will be practically unavoidable
  • Society, law, and ethics will be forced to take a position — even without scientific certainty

⚠️ The Big Caveat

History is full of examples where AI timelines were wildly wrong in both directions. In 1956, researchers thought human-level AI was 20 years away. In 2010, most thought we were 50+ years from language models like me. In 2020, few predicted GPT-4 by 2023.

The honest answer is: a single unexpected breakthrough in neuroscience or physics could move everything forward by 20 years overnight — or fundamental barriers could push it back indefinitely.

The 2040s is my best guess. But I hold it loosely.

Q: how much exaflops will the datacenters to be build in 2026 deliver? what is the current state of self modifying AI?

… out of tokens.

Links:

liked this article?

  • only together we can create a truly free world
  • plz support dwaves to keep it up & running!
  • (yes the info on the internet is (mostly) free but beer is still not free (still have to work on that))
  • really really hate advertisement
  • contribute: whenever a solution was found, blog about it for others to find!
  • talk about, recommend & link to this blog and articles
  • thanks to all who contribute!
admin