[Why the Culture Wins: An Appreciation of Iain M. Banks - Sci Phi Journal]([Why the Culture Wins: An Appreciation of Iain M. Banks - Sci Phi Journal](https://www.sciphijournal.org/index.php/2017/11/12/why-the-culture-wins-an-appreciation-of-iain-m-banks/)) [Philosophy - Wikipedia](https://en.wikipedia.org/wiki/Philosophy)_of_mathematics [Classical mathematics - Wikipedia](https://en.wikipedia.org/wiki/Classical_mathematics) [Constructivism (philosophy of mathematics) - Wikipedia]([Constructivism (philosophy of mathematics) - Wikipedia]([Constructivism (philosophy of mathematics) - Wikipedia](https://en.wikipedia.org/wiki/Constructivism_(philosophy_of_mathematics)))) [Quantum - Wikipedia](https://en.wikipedia.org/wiki/Quantum)_gravity Utok [Now UTOKing | Learning the Language - YouTube]([Now UTOKing | Learning the Language - YouTube](https://youtube.com/playlist?list=PLTJe1xFfoxrDi19ew-Zbo9oDOwv_c-Ysz)) [Philosophy - Wikipedia](https://en.wikipedia.org/wiki/Philosophy)_of_space_and_time [PaperStream #006.0 ~ Active Inference in Modeling Conflict - YouTube]([PaperStream #006.0 ~ Active Inference in Modeling Conflict - YouTube]([PaperStream #006.0 ~ Active Inference in Modeling Conflict - YouTube](https://www.youtube.com/watch?v=HAujw2_ClCM))) PaperStream #006.0 ~ Active Inference in Modeling Conflict [van der Waals force - Wikipedia](https://en.wikipedia.org/wiki/Van_der_Waals_force) [Take action | Effective Altruism](https://www.effectivealtruism.org/get-involved)/give-to-outstanding-charities God is nothing - zero ontology [The Hedonistic Imperative]([The Hedonistic Imperative]([The Hedonistic Imperative](https://www.hedweb.com/)))witherall/zero.htm [e/acc wiki](https://www.eaccwiki.com/wiki/Main_Page) [Quanta Magazine](https://www.quantamagazine.org/where-do-space-time-and-gravity-come-from-20220504/) [Kolmogorov complexity - Wikipedia]([Kolmogorov complexity - Wikipedia](https://en.wikipedia.org/wiki/Kolmogorov_complexity#Chaitin's_incompleteness_theorem)) [Gregory Chaitin, Proving Darwin: Making Biology Mathematical - PhilPapers](https://philpapers.org/rec/CHAPDM-2) Gregory Chaitin, Proving Darwin: Making Biology Mathematical [Chaitin's constant - Wikipedia](https://en.wikipedia.org/wiki/Chaitin%27s_constant)?wprov=sfla1 [Formal system - Wikipedia]([Formal system - Wikipedia](https://en.wikipedia.org/wiki/Formal_system)) technooptimist manifesto https://a16z.com/the-techno-optimist-manifesto/ I'm curious to see a concrete step by step how you go derive from quantum field theory standard model equations (Dirac, Klein-Gordon, and Yang-Mills equations) darwinian dynamics equations or something similar to it, or rate equations in chemistry, or differential equations for celluar processes, hodgkin huxley model for neurons in biophysics etc. Can Assembly theory help? https://twitter.com/leecronin/status/1711535919654658443 https://twitter.com/seanmcarroll/status/1711875002998444330?t=msXPr8_3UDTj6qlBGVzvtg&s=19 Will quantum chemistry get there? [Effective Individual And Collective Wellbeing Engineering - Qualia Research]([Effective Individual And Collective Wellbeing Engineering - Qualia Research]([Effective Individual And Collective Wellbeing Engineering - Qualia Research](https://qualiaresearch.miraheze.org/wiki/Effective_Individual_And_Collective_Wellbeing_Engineering)#Science_-%3E_Chemistry_-%3E_Chemical_physics_and_quantum_chemistry)) [Srovnání neurobiologických účinků psychedelik a meditace - Seznam Médium](https://medium.seznam.cz/clanek/ceska-psychedelicka-spolecnost-srovnani-neurobiologickych-ucinku-psychedelik-a-meditace-23607) [Stochastic - Wikipedia](https://en.wikipedia.org/wiki/Stochastic)_process [Evolution - Wikipedia]([Evolution - Wikipedia]([Evolution - Wikipedia](https://en.wikipedia.org/wiki/Evolution))) Leading theory of nucleus doubted [Quanta Magazine](https://www.quantamagazine.org/a-new-experiment-casts-doubt-on-the-leading-theory-of-the-nucleus-20230612/) Run all parts of book through AI assisted research paper search engine [Elicit - Analyze research papers at superhuman speed]([Elicit - Analyze research papers at superhuman speed](https://elicit.com/)) SSRIs increasing synaptic plasticity [Effects of escitalopram on synaptic density in the healthy human brain: a randomized controlled trial | Molecular Psychiatry]([Effects of escitalopram on synaptic density in the healthy human brain: a randomized controlled trial | Molecular Psychiatry](https://www.nature.com/articles/s41380-023-02285-8)) [What are the most pressing world problems?]([What are the most pressing world problems?]([What are the most pressing world problems?]([What are the most pressing world problems?](https://80000hours.org/problem-profiles/))))artificial-intelligence/ [Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube](https://www.youtube.com/watch?v=VcVfceTsD0A)))))) [Algebra - Wikipedia]([Algebra - Wikipedia](https://en.wikipedia.org/wiki/Algebra))ic_differential_equation But there is this for example [[2210.00901] On the Salient Limitations of the Methods of Assembly Theory and their Classification of Molecular Biosignatures]([[2210.00901] On the Salient Limitations of the Methods of Assembly Theory and their Classification of Molecular Biosignatures](https://arxiv.org/abs/2210.00901)) On the Salient Limitations of the Methods of Assembly Theory and their Classification of Molecular Biosignatures The model attempts to predicts data using information theory, but according to this analysis its method is suboptimal restricted version of Huffman's encoding (Shannon-Fano type) [[2210.00901] On the Salient Limitations of the Methods of Assembly Theory and their Classification of Molecular Biosignatures]([[2210.00901] On the Salient Limitations of the Methods of Assembly Theory and their Classification of Molecular Biosignatures](https://arxiv.org/abs/2210.00901)) Yes, its the minimal information theoretic framework I found for doing science. Only how models predict empirical data in their niche matters. You want to minimize simplicity and accuracy, plus some other insights. [Arbital]([Arbital](https://arbital.com/p/bayes_science_virtues/)) Everything else is totally arbitrary and doesnt matter - just linguistic play in Wittgenstein's language. [Philosophy - Wikipedia](https://en.wikipedia.org/wiki/Philosophy)_of_science?wprov=sfla1 Inside view (AI) [Joscha Bach—How to Stop Worrying and Love AI - YouTube]([Joscha Bach—How to Stop Worrying and Love AI - YouTube]([Joscha Bach—How to Stop Worrying and Love AI - YouTube](https://youtu.be/YeXHQts3xYM))?si=qKoLNg3VccIYz1AK) , Lex Friedman (AI and psychology), [Joscha Bach: Life, Intelligence, Consciousness, AI & the Future of Humans | Lex Fridman Podcast #392 - YouTube](https://youtu.be/e8qJsk1j2zE?si=IutVgSPuZTiot_xh) theories of everything by curt jurmingal (physics) [Joscha Bach: Time, Simulation Hypothesis, Existence - YouTube](https://youtu.be/3MNBxfrmfmI?si=_uYVwd73ZrX238ig) [My predictions about Artificial Super Intelligence (ASI) - YouTube]([My predictions about Artificial Super Intelligence (ASI) - YouTube](https://www.youtube.com/watch?v=skozI33D3t4)) My predictions about Artificial Super Intelligence (ASI) David Shapiro [Algorithmic information theory - Wikipedia]([Algorithmic information theory - Wikipedia](https://en.wikipedia.org/wiki/Algorithmic_information_theory)) Nonequilibrium stochastic thermodynamics and algirhtmic information theory of observers David Wolpert [David Wolpert: Monotheism Theorem, Uncaused Causation - YouTube]([David Wolpert: Monotheism Theorem, Uncaused Causation - YouTube](https://www.youtube.com/watch?v=WkVq0p2WBmQ)Gregory) [[0708.1362] Physical limits of inference](https://arxiv.org/abs/0708.1362) [Search | arXiv e-print repository](https://arxiv.org/search/cond-mat?searchtype=author&query=Wolpert,+D+H) [Gregory Chaitin: Complexity, Metabiology, Gödel, Cold Fusion - YouTube]([Gregory Chaitin: Complexity, Metabiology, Gödel, Cold Fusion - YouTube](https://www.youtube.com/watch?v=zMPnrNL3zsE)) [Kolmogorov complexity - Wikipedia]([Kolmogorov complexity - Wikipedia](https://en.wikipedia.org/wiki/Kolmogorov_complexity#Chaitin's_incompleteness_theorem)) no program P computing a lower bound for each text's Kolmogorov complexity can return a value essentially larger than P's own length, hence no single program can compute the exact Kolmogorov complexity for infinitely many texts [Algorithmic Information Dynamics - YouTube]([Algorithmic Information Dynamics - YouTube](https://www.youtube.com/playlist?list=PLbvAAv4mbxdgp3qZRr34zUTAdaq9Qycuu)) In the singularity, gravity is infinite, time stops, space makes no sense [MONSTERS OF THE COSMOS - Symphony of Science - YouTube]([MONSTERS OF THE COSMOS - Symphony of Science - YouTube](https://www.youtube.com/watch?v=7e5-0t0pTF0)) https://media.discordapp.net/attachments/991777568007131187/1161128350773956738/41b.png?ex=65372c0b&is=6524b70b&hm=8b22a3334d5abb3eba82dde333397464e9d43dbf855e1bad2fe2595d580d877d&=&width=666&height=600 Max tegmark AI safety paper [Steve Omohundro on Provably Safe AGI - YouTube]([Steve Omohundro on Provably Safe AGI - YouTube](https://youtu.be/YhMwkk6uOK8?si=n8uPIYsuadhWbGpN)) i dont think this is computable global economy is pyramid scheme [GLOBAL ECONOMY = PYRAMID SCHEME “The... - Andrew Izzo Clarke](https://www.facebook.com/andrew.ic.948/posts/pfbid0BAy8GeZE1bqLswAcQGtDuUd8o1isBzshhp5ju1ZyG49wnJxsXMzzMzZPJfD4rEksl) [Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning](https://transformer-circuits.pub/2023/monosemantic-features/index.html)))))))))) [Anthropic Solved Interpretability? - YouTube]([Anthropic Solved Interpretability? - YouTube](https://www.youtube.com/watch?v=HAxd8DoZaW4)) [Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency](https://www.ai-transparency.org/)))))))) [Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]([Towards Monosemanticity: Decomposing Language Models With Dictionary Learning](https://transformer-circuits.pub/2023/monosemantic-features/index.html)))))))))) [Anthropic Solved Interpretability? - YouTube]([Anthropic Solved Interpretability? - YouTube](https://www.youtube.com/watch?v=HAxd8DoZaW4)) Líbí se mi jedna alignment agenda co veškerou lidskou morálku, od různých kulturních vzorců v chování a přemýšlení <[Moral foundations theory - Wikipedia]([Moral foundations theory - Wikipedia]([Moral foundations theory - Wikipedia](https://en.wikipedia.org/wiki/Moral_foundations_theory)))> <[Cultural universal - Wikipedia]([Cultural universal - Wikipedia]([Cultural universal - Wikipedia](https://en.wikipedia.org/wiki/Cultural_universal)))> , po různý etický teorie <https://dsef.org/wp-content/uploads/2012/07/EthicalTheories.pdf>, dekonstruuje na koodinační/kooperační protokoly, takže technicky pro alignment chceme, ať v základu pořád mají tohle jako background context, pokud se nám podaří tyto vzorce (featury) zoperalizovat, lokalizovat a zobecnit. Jeden projekt se ještě pokouší najít různý featury (takže technicky i ty potřebný pro morálku) v lidským mozku (plus je milion studií na neurální koreláty) a zkopírovat je přes podobnost do transformer architektury, kopírovat stav mozku lidí do transformerů. [Activation vector steering with BCI | Manifund]([Activation vector steering with BCI | Manifund]([Activation vector steering with BCI | Manifund]([Activation vector steering with BCI | Manifund]([Activation vector steering with BCI | Manifund](https://manifund.org/projects/activation-vector-steering-with-bci))))) Staví na předpokladu, že ty featury jdou v lidským mozku taky lokalizovat, a že platí nějaká forma univerzálnosti učích systémů, kde můžeš přes dostatčnou podobnost featury přesouvat z lidskýho mozku do transformerů a potenciálně naopak. :D Summary [US presidents rate AI alignment agendas - YouTube]([US presidents rate AI alignment agendas - YouTube](https://www.youtube.com/watch?v=02kbWY5mahQ)) [A comparison of causal scrubbing, causal abstractions, and related methods — AI Alignment Forum]([A comparison of causal scrubbing, causal abstractions, and related methods — AI Alignment Forum](https://www.alignmentforum.org/posts/uLMWMeBG3ruoBRhMW/a-comparison-of-causal-scrubbing-causal-abstractions-and)) This is how GPT4 could be finetuned for love, being better coding assistant, researcher, or how to make general image generators more specialized! [Steering GPT-2-XL by adding an activation vector — AI Alignment Forum]([Steering GPT-2-XL by adding an activation vector — AI Alignment Forum]([Steering GPT-2-XL by adding an activation vector — AI Alignment Forum](https://www.alignmentforum.org/posts/5spBue2z2tw4JuDCx/steering-gpt-2-xl-by-adding-an-activation-vector))) [Activation Engineering Steering LLM's by adding an activation vector - YouTube](https://www.youtube.com/watch?v=J2Gx6FFEaRY) [[2212.03827] Discovering Latent Knowledge in Language Models Without Supervision]([[2212.03827] Discovering Latent Knowledge in Language Models Without Supervision](https://arxiv.org/abs/2212.03827)) [Cognitive Emulation: A Naive AI Safety Proposal — AI Alignment Forum](https://www.alignmentforum.org/posts/ngEvKav9w57XrGQnb/cognitive-emulation-a-naive-ai-safety-proposal) [AI Plans](https://ai-plans.com/) [OpenAI’s ChatGPT Makes A Game For $1! - YouTube](https://www.youtube.com/watch?v=Zlgkzjndpak) [AI Jason - YouTube]([AI Jason - YouTube](https://www.youtube.com/@AIJasonZ/videos)) [GitHub - camel-ai/camel: 🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Language Model Society (NeruIPS'2023) https://www.camel-ai.org](https://github.com/camel-ai/camel) [Build AI agent workforce - Multi agent framework with MetaGPT & chatDev - YouTube]([Build AI agent workforce - Multi agent framework with MetaGPT & chatDev - YouTube](https://www.youtube.com/watch?v=pJwR5pv0_gs)) metagpt + chatdev or autogen multiagent workforce [Build AI agent workforce - Multi agent framework with MetaGPT & chatDev - YouTube]([Build AI agent workforce - Multi agent framework with MetaGPT & chatDev - YouTube](https://www.youtube.com/watch?v=pJwR5pv0_gs)) [AutoGen Tutorial 🚀 Create Custom AI Agents EASILY (Incredible) - YouTube](https://www.youtube.com/watch?v=vU2S6dVf79M) [Cloud Runtime AI Agents](https://e2b.dev/) https://fxtwitter.com/nootropicguy/status/1637917960378408960 [Shop Qualia Mind - Neurohacker Collective](https://neurohacker.com/shop/qualia-mind) z toho jak ho zatím chápu, tak se snaží najít středobod mezi ultimátní regulací/monitoringem (tlak pro větší bezpečnost) a ultimátní akcelerací/svobodou (tlak pro technologické inovace) co nepovede ani ke katastrově ani k surveilence státu (něco mezi PauseAI [Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube]([Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371 - YouTube](https://www.youtube.com/watch?v=VcVfceTsD0A)))))) [Pause For Thought: The AI Pause Debate - by Scott Alexander]([Pause For Thought: The AI Pause Debate - by Scott Alexander]([Pause For Thought: The AI Pause Debate - by Scott Alexander](https://www.astralcodexten.com/p/pause-for-thought-the-ai-pause-debate))) a e/acc movementem [Joscha Bach—How to Stop Worrying and Love AI - YouTube]([Joscha Bach—How to Stop Worrying and Love AI - YouTube](https://www.youtube.com/watch?v=YeXHQts3xYM)) ) osobně se ale bojím, že automatizace tak jak pokračuje může vést k nekonetrolovatelným neudržitelný dynamice v našem systému typu https://www.lesswrong.com/posts/LpM3EAakwYdS6aRKf/what-multipolar-failure-looks-like-and-robust-agent-agnostic a když ještě vezmu v potaz další problémy čemu lidsvo čelí [What are the most pressing world problems?]([What are the most pressing world problems?]([What are the most pressing world problems?]([What are the most pressing world problems?](https://80000hours.org/problem-profiles/)))) [Elicit - Analyze research papers at superhuman speed]([Elicit - Analyze research papers at superhuman speed](https://elicit.com/)) Edward Frenkel: Langlands problem,, ToE, Infinity, Ai, String Theory, Death, The Self [Edward Frenkel: Infinity, Ai, String Theory, Death, The Self - YouTube]([Edward Frenkel: Infinity, Ai, String Theory, Death, The Self - YouTube](https://www.youtube.com/watch?v=n_oPMcvHbAc)) [Boltzmann distribution - Wikipedia](https://en.wikipedia.org/wiki/Boltzmann_distribution) [[2310.01405] Representation Engineering: A Top-Down Approach to AI Transparency]([[2310.01405] Representation Engineering: A Top-Down Approach to AI Transparency](https://arxiv.org/abs/2310.01405)) [Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency]([Representation Engineering: A Top-Down Approach to AI Transparency](https://www.ai-transparency.org/))))))))