I’ve been dedicating a fair amount of my time recently to investigating whole brain emulation (WBE).
As computational power continues to grow, the feasibility of emulating a human brain at a reasonable speed becomes increasingly plausible.
While the connectome data alone seems insufficient to fully capture and replicate human behavior, recent advancements in scanning technology have provided valuable insights into distinguishing different types of neural connections. I’ve heard suggestions that combining this neuron-scale data with higher-level information, such as fMRI or EEG, might hold the key to unlocking WBE. However, the evidence is not yet conclusive enough for me to make any definitive statements.
I’ve heard some talk about a new company aiming to achieve WBE within the next five years. While this timeline aligns suspiciously with the typical venture capital horizon for industries with weak patent protection, I believe there is a non-negligible chance of success within the next decade – perhaps exceeding 10%. As a result, I’m actively exploring investment opportunities in this company.
There has also been speculation about the potential of WBE to aid in AI alignment efforts. However, I remain skeptical about this prospect. For WBE to make a significant impact on AI alignment, it would require not only an acceleration in WBE progress but also a slowdown in AI capability advances as they approach human levels or the assumption that the primary risks from AI emerge only when it substantially surpasses human intelligence.
My primary motivation for delving into WBE stems from a personal desire to upload my own mind. The potential benefits of WBE for those who choose not to upload remain uncertain, and I’m uncertain how to predict its broader societal implications.
Here are some videos that influenced my recent increased interest. Note that I’m relying heavily on the reputations of the speakers when deciding how much weight to give to their opinions.
- AGI Risks & WBE Opportunities
- How Much Compute is Needed to Run a Human Brain Emulation
- Davidad’s somewhat less optimistic overview
Some relevant prediction markets:
- When will the human brain first be successfully emulated in full?
- Will human brain emulation be the first successful route to human-level digital intelligence?
- Full digitization (not necessarily emulation) of a human brain by 2035
- Real-time whole human brain emulation runs before end of 2038
- Human whole brain emulation before 2100?
Additionally, I’ve been working on some of the suggestions mentioned in the first video. I’m sharing my code and analysis on Colab. My aim is to evaluate the resilience of language models to the types of errors that might occur during the brain scanning process. While the results provide some reassurance, their value heavily relies on assumptions about the importance of low-confidence guesses made by the emulated mind.
This is the first blog post of it’s kind that I have seen on the Internet. WBE is a big deal, so it’s exciting to see investors taking the idea seriously. Thank you for the information and perspective.
Could you outline your reasons for thinking…
(1) that WBE is feasible in terms of (i) emulation accuracy and (ii) the amount of compute required not being astronomical, and
(2) that copying a brain without destroying it is feasible in the next few decades (you seem to weakly imply that you think so, since you call it “uploading” rather than, say, “digital afterlife”)