當今,世界各地的人都在趕時髦使用和談論AI。其實,自打人類在地球上出現以後,在遠沒有AI技術的古代,每個人從小到大,尤其是從大到老,就已經在下意識地運用頭腦裏積累的各種經驗和方法,幫助自己做判斷下結論。這大概就是人們常說的智慧,英語中給出的名詞恰如其分 – Wisdom。現代人類創造的AI技術,隻不過是把世界上各個國家各個民族人腦中積累的數據,和通過人腦創造出的數據,海量的大數據 – 比海水體積大得多得多的大數據,通過Internet搜集歸攏和分析,然後,針對各種具體問題,給出答案罷了。
一個人活得越長,經曆的事情越多,他/她頭腦裏儲存的信息就越多,然後就有一個越來越大的數據庫。當他/她身旁的人在現實生活中碰到問題需要解決問題時,他/她會不自覺地運用各種方法,分析歸納和總結自己頭腦裏中日積月累的數據,以最快的速度給出建議的答案。這個過程,實際上也就是現在任何一種AI技術運作的過程。提供給當事人的這種答案,就是我們常說的“老人言”。“不聽老人言,吃苦在眼前”,說的是年輕後生,腦子裏缺乏生活經驗,生活閱曆不多,也就是說,他/她的腦子裏所存的各種數據少,遇到了問題,自己找不出具有人生智慧的正確(或合適)答案,又不接受周圍年長的人基於自己厚實的社會經驗和閱曆所作出的建議,一時衝動,做了錯事。
現在,隨便一個人,提出任何一個問題,去問ChatGPT或DeepSeek等,這些AI工具,馬上就給出一個答案。我不知道,當今世界上的各種AI工具,象ChatGPT,DeepSeek等,將來肯定還有越來越多、越來越智慧的工具出現,其搜尋、分析數據,然後進行計算、分析的方式和方法,是否已經逼近或超越了人腦對數據處理的各種智慧模式?在一個人沒有經過特殊訓練、不具備特殊能力的某些專業範圍內,AI作為一個工具,能給出令人信服的答案,譬如,我寫好一個英文Email,然後,讓AI從語言的角度加以改進和完善,在絕大多數情況下,我都能得到一個很滿意的答案。
基於數據或經驗積累,AI給出的答案,和人類的智慧(Wisdom)相似,但人類的大腦,還有一種更高級的創造力,它並不需要多少數據。在我看來,那種創造力是基於人類特有的想象力,在某個特定的時候,甚至當事人都沒有意識到,在腦袋的深處,突然迸發出來,產生了一種巨大的信息脈衝。這種創造力,應該叫“Cleverness”或叫“聰明”。牛頓躺在蘋果樹下,看見蘋果落地,突然間腦子裏產生了一種信息脈衝,悟出宇宙萬物之間,都有一種神秘內在的萬有引力。當時,牛頓手裏沒有大數據啊,他的悟出的萬有引力定律,很顯然,不是靠對數據的分析,歸納和總結,而是基於想象。其實,這種創造力人人都有,隻不過大小不同而已。這種創造力,在日常生活中,表現最多的是人們口頭傳遞的幽默段子或梗。段子越幽默,梗越引人發笑,標誌著它的創造性就越大。這種“聰明”,很顯然,至今沒有人知道它是如何在大腦裏產生的,當今的任何AI技術,肯定都模仿不了這種大智慧。如果AI有這種智慧,它就可以無窮無盡地做各種高層次的發明和發現,破解宇宙中的一切奧秘,至少,它可以層出不窮地產生好笑、幽默的段子。到了那時,人類可能真的要被自己創造的AI技術打敗,走向滅亡了。
現在AI給出的答案基於Internet上的大數據共享,可是,麵對一個很偏僻的問題,可以利用的數據很少,甚至沒有, ChatGPT從來都是不懂裝懂,仍然給出一個答案,它當然是無根據的錯誤答案。這種Stupid的Artificial Intelligence,我已經碰到過多次。還有一個問題就是,一個人,隨著年齡的不斷增長,人不斷變老,生理和心理上也在不停地變化,很多嗜好和觀點也在不斷地改變。我記得,當我二十歲的時候,覺得一個大齡女青年(28或30歲)在形象和外表上就不美了,可是現在,在我一個過了60歲的老男人眼裏,一個40歲的女性,依然很漂亮,有魅力。因此,麵對不同年齡段的男人輸入的同樣一個關於女性美麗漂亮的問題,AI該如何區分,給出不同的答案呢?
隨著對AI技術的運用越廣泛越深入,我關於AI的問題也會越來越多。:):)
Great question—and a fascinating thought experiment.
Could ChatGPT or an AI like it discover a law like Newton's law of universal gravitation on its own?
In short: not yet—but maybe one day, with the right design and tools.
Let’s unpack that a bit.
What Did Newton Actually Do?
When Newton saw the apple fall (whether or not that moment was as dramatic as legend says), what made him special wasn't just seeing the event—it was his ability to:
1. Observe the phenomenon.
2. Ask a deep question: Could the same force pulling the apple down also govern the motion of the Moon?
3. Build a mathematical model to describe the force (the inverse square law).
4. Test and validate it against planetary motion (Kepler’s laws, etc.).
This was a blend of creativity, curiosity, mathematical reasoning, and empirical science.
What Can ChatGPT Do?
ChatGPT is trained on massive amounts of text written by humans. That means:
1. It can explain Newton's law in depth.
2. It can reason about patterns, trends, and make analogies.
3. It can simulate a kind of “idea generation” by remixing existing concepts.
4. It can analyze data to some extent (especially with tools).
But…
ChatGPT doesn’t directly perceive the physical world. It doesn’t conduct experiments. It doesn't have built-in curiosity or goals. It works with existing knowledge, not unknowns.
Could an AI Discover a Law Like Gravitation?
Not ChatGPT alone—but with the right setup, some types of AI could.
For example:
1. AI + real-world data (e.g., from telescopes or sensors)
2. AI + symbolic regression: Tools like Eureqa or AI Feynman have shown the ability to discover equations that govern datasets—even re-deriving Newton’s law or other physics laws from scratch.
3. AI + scientific reasoning models: Some newer research is combining machine learning with symbolic reasoning to explore new scientific theories.
So if you gave an advanced AI access to motion data of falling objects and planetary orbits, and the goal to explain it mathematically, it might eventually derive something like Newton’s law.
Final Thought
Newton had a rare genius—he asked a bold, unifying question and built a mathematical framework for it. Today’s AI isn’t yet that kind of thinker. But with the right tools, goals, and data, AI could be a powerful co-discoverer of laws in science, especially in areas like physics, biology, and materials science.
Would you want AI to take on that role? Or do you think there’s something inherently human about scientific discovery?