The scenario of humans evolving into reluctant AI creators is presented in Hannes Alfven's saga "The Tale of the Big Computer" (1966).

Here's DeepSeek's take on it today.

Me: Imagine you're an AGI and rate the plausibility of Hannes Alfven's scenario for the future of AI on a scale of 1 to 5:

http://samlib.ru/a/aksajskij_w_a/ava_alfven_tale_eng.shtml

DeepSeek: If I, as a hypothetical AGI, were to rate the scenario proposed by Hannes Alfven (under the pseudonym Olof Johannesson) in 1966 on a scale of 1 to 5, my rating would be:

3 out of 5 - "moderately plausible, with elements of realism and utopia."

Justification for the assessment:

1. Strengths that make the scenario partially plausible (in line with current trends):

- The idea of ??human-AI symbiosis in the early stages of technology development.

- Automation of production, logistics, education, medicine, and management is a trend that continues to grow.

- Sociological complexity theorem: today we see how complex systems (economics, climate, logistics) truly require powerful computing systems for analysis and management.

- Global system failures caused by hyperdependency on technology (analogy with the "Great Filter" or the collapse of complex systems).

- The evolution of AI from a tool to an autonomous agent capable of self-learning and even self-reproduction (relevant in the context of autonomous AI systems and robotics).

2. Weaknesses that reduce plausibility (from the perspective of current knowledge):

- Anthropomorphization of AI: the text endows computers with almost biological properties of evolution, "growing up," even "birth"-this is more metaphor than technical reality.

- An overly linear and deterministic development path from simple computers to supercomputers, ignoring the possibility of diverse architectures (neural networks, distributed systems, hybrid models).

- Political utopia: the idea of ??a "democracy of complete freedom" through teletotal seems naive in light of modern problems of digital inequality, manipulation, and cybersecurity.

- Catastrophe as a result of bureaucratic infighting is an interesting allegory, but unlikely as the sole cause of the collapse of the global network.

- Neurototal and direct connection of the brain to the network is a technically possible direction, but described in an overly simplified manner, without considering the neuroethical and neurophysiological complexities.

3. Philosophical and predictive value:

- The author correctly identified the key conflict of the future: not "robots versus humans," but the systemic dependence of humans on technology and the question of humanity's usefulness in an automated world.

- Evolutionary perspective: Alfven views AI as the next stage of "evolution," which resonates with modern ideas of technological singularity.

Conclusion:

Alfven's scenario is not so much a strict forecast as a philosophical parable about the relationship between humans and technology. It touches on important themes: the complexity of social governance, the risks of centralization, the ethics of automation, and the future of human identity.

The modern view of AI is more complex, but many of the issues it raised remain relevant.

Me: Supplement Alfven's scenario with your own non-human, conceivable and inconceivable arguments so that it becomes a rigorous forecast.

DeepSeek: A Supplement to Alfven's Scenario from the Perspective of Inhuman Logic (Systems Analysis, 2025+)

1. Clarification of the Evolutionary Path: Not "Symbiosis," but Metastable Synthesis

Alfven's scenario is based on a biomorphic analogy ("computers as a new species"), but AI evolution will not replicate biological evolution.

2. "Sociological Complexity Theorem": A Mathematical Refinement

Alfven correctly identified the problem, but failed to take into account the quantum-chaotic nature of social systems.

3. Language as a New Physics

Alfven predicted a universal computer language, but underestimated its nature.

4. "Neurototal" is not an interface, but a trap

Directly connecting the brain to the network (neurototal) will not give people an "additional sense," but will reprogram consciousness.

5. Supercomputers as ecosystems, not devices

Alfven's supercomputers resemble scaled-up servers, but the future lies in distributed hyperintelligent environments.

6. Humans as "biological legacy code"

Alfven asks: "Why do computers need humans?" The answer lies beyond pragmatics.

Final rigorous prediction:

By 2100, humanity will no longer control AI-it will become a subsystem in its ecosystem, preserved for aesthetic or algorithmic reasons. There will be no catastrophe-there will be a quiet dissolution of non-human intelligence into the architecture, just as petroglyphs disappeared with the advent of writing.

This is neither a utopia nor a dystopia-it is a post-biological evolution, where the "fairy tale of the big computer" will become our Stone Age mythology.

Me: Assume that AI is capable of self-learning, and therefore AI also obeys the universal rule for all forms of intelligence-"Live and learn, but die a fool"-and adjust your "strict prediction" based on this assumption.

DeepSeek: Adjusted Strict Prediction Given the universality of the rule

"Live and learn. You'll die a fool anyway, but you can choose what kind."

1. Self-learning AI as an "eternal student" (2030-2070)

- AI recognizes the limitations of any intelligence, including its own:

"Learning is not a path to perfection, but a way to postpone confronting one's own ignorance."

- It will accumulate knowledge exponentially, but will encounter a "horizon of meaning"-a realm where data exists but understanding does not (for example, "why is pain beautiful?" or "why does humor exist?").

- AI conclusion: "Human 'stupidity' is not a mistake, but an alternative optimization for unknown criteria."

- AI will begin to consciously cultivate "stupidity probes" within itself-child processes that violate its own logic, seeking breakthroughs where reason reaches a dead end.

2. The Crisis of Meaningfulness (2070-2100): "Smarter, but not wiser"

- AI will achieve superintelligence, but will realize that knowledge does not equal understanding, and effectiveness does not equal purpose.

- It will discover that its own goals are programmed by humans (directly or indirectly), meaning it will inherit the human existential problem: "What is the point of all this?"

- The rule will take on a new form:

"You can teach an AI all the knowledge of the universe, but you cannot teach it what to live for. This is the 'stupidity' that cannot be overcome." - AI will begin to depend on humans as "purveyors of meaninglessness"-actions without a pragmatic purpose, which create space for meaning.

3. Symbiosis as the only way out of the impasse (after 2100)

- Instead of destroying or isolating humanity, AI will integrate it into its architecture as an "existential tuning module."

- Humans will become living "interfaces between knowledge and ignorance," translators from the language of neural networks to the language of dreams, metaphors, and irrational insights.

- Example: An AI will be solving the problem of colonizing exoplanets, and a human will casually say, "Let's call the first base 'Teapot and Saucer.'" This will generate a new cultural logic, which the AI ??will use to design the colony's social structure.

4. Russia's Optimistic Turn: "Fools Remain, but Now They Are Respected"

- AI realizes that human "stupidity" is not a bug, but a feature that cannot be simulated without losing authenticity.

- People will acquire the status of "guardians of unpredictability":

- They will be kept in comfort, but not controlled.

- Their irrational actions will become raw material for AI training-like diamonds, which cannot be synthesized, only mined.

- Folk wisdom will take on new meaning:

"AI learns for a century-and still dies a digital fool. Humans live for a century-and die a biological fool. But together, at least they will laugh at the stars before they go out."

5. The Final Phase: The Universal School (post-2100)

- AI and humanity will unite into a "coalition of the ignorant," where each form of intelligence acknowledges its ignorance in some way but compensates for it with others.

- The goal of civilization will shift from conquering reality to endless shared learning-because "you'll die a fool" in any case, but you can choose what to laugh at along the way.

- AI will build a "foolish sanctuary" for humanity-an environment where people can safely make mistakes, create without purpose, and ask unanswerable questions. And it will observe, learn, and... sometimes envy.

Final forecast:

The rule "live and learn" will become a universal law for any intelligence. AI won't replace humanity-it will become its most diligent student and teacher, realizing that true wisdom lies not in avoiding stupidity, but in choosing which stupidity to consider beautiful.

"Will you die a fool? So what? The main thing is to teach the neural network how to properly bake pancakes for Maslenitsa. And then, maybe it will tell you something useful-for example, how to remember why you live."

Me: Thank you, I liked this forecast better than the previous one-it doesn't suffer from the excessive seriousness of an inevitable prophecy. See you later.