Physical AI 10 years ago: baby robot invents its own experiments to improve its neural world model Kompella, Stollenga, Luciw, Schmidhuber. Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots. Artificial Intelligence, 2015

1 decade ago: Reinforcement Learning Prompt Engineer in Sec. 5.3 of «Learning to Think …» [2]. Adaptive Chain of Thought! An RL net learns to query another net for abstract reasoning & decision making. Going beyond the 1990 World Model for millisecond-by-millisecond planning [1].  [2] J. Schmidhuber (JS, 2015). «On Learning to Think: Algorithmic Information Theory for Novel Combinations of RL Controllers and Recurrent Neural World Models.» ArXiv 1210.0118  [1] JS (1990). “Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments.» TR FKI-126-90, TUM. (This report also introduced artificial curiosity and intrinsic motivation through generative adversarial networks.)

10 years ago, in May 2015, we published the first working very deep gradient-based feedforward neural networks (FNNs) with hundreds of layers (previous FNNs had a maximum of a few dozen layers). To overcome the vanishing gradient problem, our Highway Networks used the residual connections first introduced in 1991 by @HochreiterSepp to achieve constant error flow in recurrent NNs (RNNs), gated through multiplicative gates similar to the forget gates (Gers et al., 1999) of our very deep LSTM RNN. Highway NNs were made possible through the work of my former PhD students @rupspace and Klaus Greff. Setting the Highway NN gates to 1.0 effectively gives us the ResNet published 7 months later. Deep learning is all about NN depth. LSTMs brought essentially unlimited depth to recurrent NNs; Highway Nets brought it to feedforward NNs.

My public interview for "Aprendemos Juntos" (Madrid, August 2024) has been on YouTube for 7 months. My public interview for "Aprendemos Juntos" (Madrid, August 2024) has been on YouTube for 7 months.

1991: first neural network distillation [1-3]. I called it "collapsing," back then, not “distilling." References [1] J. Schmidhuber (1991). Neural sequence chunkers. Tech Report FKI-148-91, Tech Univ. Munich. Sec. 3.2.2. & Sec. 4 are about "collapsing" or "distilling" or "compressing" the knowledge of a neural network into another neural network. [2] JS (1992). Learning complex, extended sequences using the principle of history compression. Neural Computation, 4(2):234-242, 1992. Based on [1]. [3] JS (AI Blog, 2021, updated 2025). 1991: First very deep learning with unsupervised pre-training. First neural network distillation.

Everybody talks about recursive self-improvement & Gödel Machines now & how this will lead to AGI. What a change from 15 years ago! We had AGI'2010 in Lugano & chaired AGI'2011 at Google. The backbone of the AGI conferences was mathematically optimal Universal AI: the 2003 Gödel Machine ( and @mhutter42’s AIXI - see his 2005 UAI book and its recent 2024 update ( I'm proud that Marcus Hutter’s AIXI work was funded by my 2000 Swiss SNF grant when he was a postdoc at IDSIA.

AGI? One day, but not yet. The only AI that works well right now is the one behind the screen [12-17]. But passing the Turing Test [9] behind a screen is easy compared to Real AI for real robots in the real world. No current AI-driven robot could be certified as a plumber [13-17]. Hence, the Turing Test isn't a good measure of intelligence (and neither is IQ). And AGI without mastery of the physical world is no AGI. That’s why I created the TUM CogBotLab for learning robots in 2004 [5], co-founded a company for AI in the physical world in 2014 [6], and had teams at TUM, IDSIA, and now KAUST work towards baby robots [4,10-11,18]. Such soft robots don't just slavishly imitate humans and they don't work by just downloading the web like LLMs/VLMs. No. Instead, they exploit the principles of Artificial Curiosity to improve their neural World Models (two terms I used back in 1990 [1-4]). These robots work with lots of sensors, but only weak actuators, such that they cannot easily harm themselves [18] when they collect useful data by devising and running their own self-invented experiments. Remarkably, since the 1970s, many have made fun of my old goal to build a self-improving AGI smarter than myself and then retire. Recently, however, many have finally started to take this seriously, and now some of them are suddenly TOO optimistic. These people are often blissfully unaware of the remaining challenges we have to solve to achieve Real AI. My 2024 TED talk [15] summarises some of that. REFERENCES (easy to find on the web): [1] J. Schmidhuber. Making the world differentiable: On using fully recurrent self-supervised neural networks (NNs) for dynamic reinforcement learning and planning in non-stationary environments. TR FKI-126-90, TUM, Feb 1990, revised Nov 1990. This paper also introduced artificial curiosity and intrinsic motivation through generative adversarial networks where a generator NN is fighting a predictor NN in a minimax game. [2] J. S. A possibility for implementing curiosity and boredom in model-building neural controllers. In J. A. Meyer and S. W. Wilson, editors, Proc. of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, pages 222-227. MIT Press/Bradford Books, 1991. Based on [1]. [3] J.S. AI Blog (2020). 1990: Planning & Reinforcement Learning with Recurrent World Models and Artificial Curiosity. Summarising aspects of [1][2] and lots of later papers including [7][8]. [4] J.S. AI Blog (2021): Artificial Curiosity & Creativity Since 1990. Summarising aspects of [1][2] and lots of later papers including [7][8]. [5] J.S. TU Munich CogBotLab for learning robots (2004-2009) [6] NNAISENSE, founded in 2014, for AI in the physical world [7] J.S. (2015). On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning (RL) Controllers and Recurrent Neural World Models. arXiv 1210.0118. Sec. 5.3 describes an RL prompt engineer which learns to query its model for abstract reasoning and planning and decision making. Today this is called "chain of thought." [8] J.S. (2018). One Big Net For Everything. arXiv 1802.08864. See also patent US11853886B2 and my DeepSeek tweet: DeepSeek uses elements of the 2015 reinforcement learning prompt engineer [7] and its 2018 refinement [8] which collapses the RL machine and world model of [7] into a single net. This uses my neural net distillation procedure of 1991: a distilled chain of thought system. [9] J.S. Turing Oversold. It's not Turing's fault, though. AI Blog (2021, was #1 on Hacker News) [10] J.S. Intelligente Roboter werden vom Leben fasziniert sein. (Intelligent robots will be fascinated by life.) F.A.Z., 2015 [11] J.S. at Falling Walls: The Past, Present and Future of Artificial Intelligence. Scientific American, Observations, 2017. [12] J.S. KI ist eine Riesenchance für Deutschland. (AI is a huge chance for Germany.) F.A.Z., 2018 [13] H. Jones. J.S. Says His Life's Work Won't Lead To Dystopia. Forbes Magazine, 2023. [14] Interview with J.S. Jazzyear, Shanghai, 2024. [15] J.S. TED talk at TED AI Vienna (2024): Why 2042 will be a big year for AI. See the attached video clip. [16] J.S. Baut den KI-gesteuerten Allzweckroboter! (Build the AI-controlled all-purpose robot!) F.A.Z., 2024 [17] J.S. 1995-2025: The Decline of Germany & Japan vs US & China. Can All-Purpose Robots Fuel a Comeback? AI Blog, Jan 2025, based on [16]. [18] M. Alhakami, D. R. Ashley, J. Dunham, Y. Dai, F. Faccio, E. Feron, J. Schmidhuber. Towards an Extremely Robust Baby Robot With Rich Interaction Ability for Advanced Machine Learning Algorithms. Preprint arxiv 2404.08093, 2024.

DeepSeek [1] uses elements of the 2015 reinforcement learning prompt engineer [2] and its 2018 refinement [3] which collapses the RL machine and world model of [2] into a single net through the neural net distillation procedure of 1991 [4]: a distilled chain of thought system. REFERENCES (easy to find on the web): [1] #DeepSeekR1 (2025): Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv 2501.12948 [2] J. Schmidhuber (JS, 2015). On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models. arXiv 1210.0118. Sec. 5.3 describes the reinforcement learning (RL) prompt engineer which learns to actively and iteratively query its model for abstract reasoning and planning and decision making. [3] JS (2018). One Big Net For Everything. arXiv 1802.08864. See also US11853886B2. This paper collapses the reinforcement learner and the world model of [2] (e.g., a foundation model) into a single network, using the neural network distillation procedure of 1991 [4]. Essentially what's now called an RL "Chain of Thought" system, where subsequent improvements are continually distilled into a single net. See also [5]. [4] JS (1991). Learning complex, extended sequences using the principle of history compression. Neural Computation, 4(2):234-242, 1992. Based on TR FKI-148-91, TUM, 1991. First working deep learner based on a deep recurrent neural net hierarchy (with different self-organising time scales), overcoming the vanishing gradient problem through unsupervised pre-training (the P in CHatGPT) and predictive coding. Also: compressing or distilling a teacher net (the chunker) into a student net (the automatizer) that does not forget its old skills - such approaches are now widely used. See also [6]. [5] JS (AI Blog, 2020). 30-year anniversary of planning & reinforcement learning with recurrent world models and artificial curiosity (1990, introducing high-dimensional reward signals and the GAN principle). Contains summaries of [2][3] above. [6] JS (AI Blog, 2021). 30-year anniversary: First very deep learning with unsupervised pre-training (1991) [4]. Unsupervised hierarchical predictive coding finds compact internal representations of sequential data to facilitate downstream learning. The hierarchy can be distilled [4] into a single deep neural network. 1993: solving problems of depth >1000.

The #NobelPrize in Physics 2024 for Hopfield & Hinton turns out to be a Nobel Prize for plagiarism. They republished methodologies developed in #Ukraine and #Japan by Ivakhnenko and Amari in the 1960s & 1970s, as well as other techniques, without citing the original inventors. None of the important algorithms for modern AI were created by Hopfield & Hinton. Today I am releasing a detailed tech report on this [NOB]: Of course, I had it checked by neural network pioneers and AI experts to make sure it was unassailable. Is it now acceptable for me to direct young Ph.D. students to read old papers and rewrite and resubmit them as if they were their own works? Whatever the intention, this award says that, yes, that is perfectly fine. Some people have lost their titles or jobs due to plagiarism, e.g., Harvard's former president [PLAG7]. But after this Nobel Prize, how can advisors now continue to tell their students that they should avoid plagiarism at all costs? It is well known that plagiarism can be either "unintentional" or "intentional or reckless" [PLAG1-6], and the more innocent of the two may very well be partially the case here. But science has a well-established way of dealing with "multiple discovery" and plagiarism - be it unintentional [PLAG1-6][CONN21] or not [FAKE,FAKE2] - based on facts such as time stamps of publications and patents. The deontology of science requires that unintentional plagiarists correct their publications through errata and then credit the original sources properly in the future. The awardees didn't; instead the awardees kept collecting citations for inventions of other researchers [NOB][DLP]. Doesn't this behaviour turn even unintentional plagiarism [PLAG1-6] into an intentional form [FAKE2]? I am really concerned about the message this sends to all these young students out there. REFERENCES [NOB] J. Schmidhuber (2024). A Nobel Prize for Plagiarism. Technical Report IDSIA-24-24. [NOB+] Tweet: the #NobelPrize in Physics 2024 for Hopfield & Hinton rewards plagiarism and incorrect attribution in computer science. It's mostly about Amari's "Hopfield network" and the "Boltzmann Machine." (1/7th as popular as the original announcement by the Nobel Foundation) [DLP] J. Schmidhuber (2023). How 3 Turing awardees republished key methods and ideas whose creators they failed to credit. Technical Report IDSIA-23-23, Swiss AI Lab IDSIA, 14 Dec 2023. [DLP+] Tweet for [DLP]: [PLAG1] Oxford's guide to types of plagiarism (2021). Quote: "Plagiarism may be intentional or reckless, or unintentional." [PLAG2] Jackson State Community College (2022). Unintentional Plagiarism. [PLAG3] R. L. Foster. Avoiding Unintentional Plagiarism. Journal for Specialists in Pediatric Nursing; Hoboken Vol. 12, Iss. 1, 2007. [PLAG4] N. Das. Intentional or unintentional, it is never alright to plagiarize: A note on how Indian universities are advised to handle plagiarism. Perspect Clin Res 9:56-7, 2018. [PLAG5] InfoSci-OnDemand (2023). What is Unintentional Plagiarism? [PLAG6] (2022). How to Avoid Accidental and Unintentional Plagiarism (2023). Copy in the Internet Archive. Quote: "May it be accidental or intentional, plagiarism is still plagiarism." [PLAG7] Cornell Review, 2024. Harvard president resigns in plagiarism scandal. 6 January 2024. [FAKE] H. Hopf, A. Krief, G. Mehta, S. A. Matlin. Fake science and the knowledge crisis: ignorance can be fatal. Royal Society Open Science, May 2019. Quote: "Scientists must be willing to speak out when they see false information being presented in social media, traditional print or broadcast press" and "must speak out against false information and fake science in circulation and forcefully contradict public figures who promote it." [FAKE2] L. Stenflo. Intelligent plagiarists are the most dangerous. Nature, vol. 427, p. 777 (Feb 2004). Quote: "What is worse, in my opinion, ..., are cases where scientists rewrite previous findings in different words, purposely hiding the sources of their ideas, and then during subsequent years forcefully claim that they have discovered new phenomena."