Knowledge graphs are really cool 🧠 What’s even cooler... is LLMs + knowledge graphs backed by a graph db (NebulaGraph) 🔥 This presents an entirely new stack for retrieval-augmented generation (separate from vector db + top-k)! Now possible with LlamaIndex 🦙 👇show more

V8 DKG Launches Now: A New Dawn for AI... in 2025🌟 As 2024 draws to a close, we're excited to announce the immediate launch of V8 Decentralized Knowledge Graph (DKG)! This monumental release is set to redefine AI's capabilities as we step into 2025. What Does V8 Bring to the Table? 🧠Decentralized AI: AI agents can now leverage a 'collective memory' at internet scale, drawing from a shared, yet sovereign, knowledge base. This means AI can provide more contextual, coherent, and accurate interactions without compromising data integrity or privacy. 🚀Unmatched Scalability: With the capability to handle billions of Knowledge Assets, V8 DKG sets the stage for AI to grow and learn in ways we've only imagined, supporting everything from decentralized science to industry 4.0. 🔐Trust and Integrity: With integrated decentralized Retrieval Augmented Generation (dRAG), V8 DKG promotes AI that's more accurate, less biased, and inherently trustworthy. How to V8👇 To update your node from V6 to V8, delegate your TRAC utility tokens, and learn more about creating, connecting and owning your Knowledge Assets, make sure to thoroughly read the following documentation: 👉 With V8 DKG launch, you may now access the new: V8 Explorer👉 AND Staking Dashboard 👉 You may now also participate in V8 Staking Security Bounty by delegating new TRAC stake and report your findings. Read more: 👉 The V8 Staking Security Bounty will importantly contribute to the so-called tuning phase of V8 DKG launch (V8.0 to V8.1). Let's break records, as we usher in a new era of Internet Scale OriginTrail!show more

For 41 years, to find shortest paths in a... graph, the Dijkstra’s algorithm, was seen as the best possible way. Not any longer: Now a team from Tsinghua University has beaten it. They created the first faster algorithm for directed shortest paths since 1984. • Faster than Dijkstra on large sparse graphs • Works with real, non-negative edge weights • Proves that sorting is not the main bottleneck anymore Shortest-path algorithms power maps, GPS, logistics, networking, and robotics. This result shows that even the most “finished” algorithms can still be improved. Thanks for sharing, Md Ismail Šojal 🕷️! 📍 Paper: —— Weekly robotics and AI insights. Subscribe free:show more

Vector Database by Hand ✍️ Vector databases are revolutionizing... how we search and analyze complex data. They have become the backbone of Retrieval Augmented Generation (#RAG). How do vector databases work? [1] Given ↳ A dataset of three sentences, each has 3 words (or tokens) ↳ In practice, a dataset may contain millions or billions of sentences. The max number of tokens may be tens of thousands (e.g., 32,768 mistral-7b). Process "how are you" [2] 🟨 Word Embeddings ↳ For each word, look up corresponding word embedding vector from a table of 22 vectors, where 22 is the vocabulary size. ↳ In practice, the vocabulary size can be tens of thousands. The word embedding dimensions are in the thousands (e.g., 1024, 4096) [3] 🟩 Encoding ↳ Feed the sequence of word embeddings to an encoder to obtain a sequence of feature vectors, one per word. ↳ Here, the encoder is a simple one layer perceptron (linear layer + ReLU) ↳ In practice, the encoder is a transformer or one of its many variants. [4] 🟩 Mean Pooling ↳ Merge the sequence of feature vectors into a single vector using "mean pooling" which is to average across the columns. ↳ The result is a single vector. We often call it "text embeddings" or "sentence embeddings." ↳ Other pooling techniques are possible, such as CLS. But mean pooling is the most common. [5] 🟦 Indexing ↳ Reduce the dimensions of the text embedding vector by a projection matrix. The reduction rate is 50% (4->2). ↳ In practice, the values in this projection matrix is much more random. ↳ The purpose is similar to that of hashing, which is to obtain a short representation to allow faster comparison and retrieval. ↳ The resulting dimension-reduced index vector is saved in the vector storage. [6] Process "who are you" ↳ Repeat [2]-[5] [7] Process "who am I" ↳ Repeat [2]-[5] Now we have indexed our dataset in the vector database. [8] 🟥 Query: "am I you" ↳ Repeat [2]-[5] ↳ The result is a 2-d query vector. [9] 🟥 Dot Products ↳ Take dot product between the query vector and database vectors. They are all 2-d. ↳ The purpose is to use dot product to estimate similarity. ↳ By transposing the query vector, this step becomes a matrix multiplication. [10] 🟥 Nearest Neighbor ↳ Find the largest dot product by linear scan. ↳ The sentence with the highest dot product is "who am I" ↳ In practice, because scanning billions of vectors is slow, we use an Approximate Nearest Neighbor (ANN) algorithm like the Hierarchical Navigable Small Worlds (HNSW).show more

⭐The Year of Inference is here. Featherless is now... an official inference provider on Hugging Face, unlocking 6,700+ LLMs for anyone to run, eval, and deploy instantly. It all starts with accessibility. From DeepSeek to Mistral, LLaMA to Qwen — powerful LLMs are one click away. We believe the future of AI is shaped by the long tail: personalized, specialized models tuned to real people’s needs. To get there, inference must be open, affordable, and usable by all. Whether you're fine-tuning, prototyping, or scaling a product, this moment is for you. 🫱🏻‍🫲🏻Let’s make inference the easiest part of building with AI. 📢 Share this so more builders know what’s now possible. Excited to be partnering with clem 🤗 Julien Chaumond Vaibhav (VB) Srivastav Simon Brandeis & Hugging Face team to take this to the next level!show more

Look what they put on my hamburger! 🍔 Young... children aren’t the only ones who make sense of the world by connecting new experiences with prior knowledge - it’s just that there are so many new experiences to be had at their age. Take this little one, who has opened her cheeseburger only to find that it is unexpectedly covered with small, white, rectangular objects. Drawing on her prior knowledge of objects matching this same description, she makes a well-reasoned (if inadvertently hilarious) inference: someone at the restaurant has covered her burger with TEETH! 🦷 🦷 🦷 What an amazing window on her thinking. In this case she’ll have to accommodate for some new learning today: adding onions to her mental inventory of small, white, rectangles. But for now her reasoning is more than just funny. It’s really quite clever. Has your child ever encountered something new, only to mistake it for something to which they’d already been exposed? I’d love to hear your stories! 🎥 This amazing video - and genius little learner - was shared on TT by brandywilson566.show more

I’m starting a company. An internet-scale dataset is created... every day that can be used to cure diseases. ㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤ Yet decisions for developing new drugs use a tiny fraction of it. ㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤ After years of building and investing in therapeutics companies, I'm convinced that this is about to change. ​ · ​ There are two kinds of knowledge. Facts, and connections. We have an abundance of known facts about biology, but we have barely begun to make all the connections. ㅤ Our company is connecting the world's pharmaceutical data, drawing a coherent understanding from an archipelago of information. ​ Thousands of decisions behind breakthrough drugs—from experimental design to new product planning—can be augmented by this scientific intelligence. ​ · ​ We are partnering with drug developers who’ve dedicated their careers to their craft. ​ We know that engineering tools for those at the pinnacle of human expertise is not going to be easy. ​ But it will change how life-saving discoveries are brought to patients. ​ If this sounds like fun, reach out. We're recruiting founding engineers.show more

Young children are like scientists - constantly testing their... theories about the world. Swiss psychologist Jean Piaget is revered in education circles as the father of “constructivism” - which is a theory that young children create knowledge by connecting new experiences with past learning, through a process not unlike the scientific method. And here’s an amazing example. Faced with something unfamiliar (an anti-theft security tag affixed to a shoe), this little guy draws upon his existing knowledge (or “schema” in Piagetian terms) to make sense of what he’s seeing. In a sign of the times that would have fascinated Piaget (who died in 1980), our hero assumes that the shoe comes with its own charger, which - according to its label (a size 10 sticker) will permit the owner to walk for 10 minutes after charging. (Or perhaps this is the time required to achieve a full charge?) It’s really a pretty amazing hypothesis that draws on multiple different data points. Not shown in the video is what happens next. Had his theory been affirmed as correct (which in this case it isn’t), the example of a battery powered shoe with a USB port would have been “assimilated,” strengthening his existing knowledge of electronic devices. Presuming mom provides some explanation about store security tags, however, our little scientist will be disproven - forcing him to “accommodate” within his existing schema to take the existence of a new object into account. Either way, knowledge is being constructed. What an impressive little guy! 🧠 Have you noticed your children test their theories about the world? If so how? 🎥 hannahs_journeys IGshow more

Young children are like scientists - constantly testing their... theories about the world. Swiss psychologist Jean Piaget is revered in education circles as the father of “constructivism” - which is a theory that young children create knowledge by connecting new experiences with past learning, through a process not unlike the scientific method. And here’s an amazing example. Faced with something unfamiliar (an anti-theft security tag affixed to a shoe), this little guy draws upon his existing knowledge (or “schema” in Piagetian terms) to make sense of what he’s seeing. In a sign of the times that would have fascinated Piaget (who died in 1980), our hero assumes that the shoe comes with its own charger, which - according to its label (a size 10 sticker) will permit the owner to walk for 10 minutes after charging. (Or perhaps this is the time required to achieve a full charge?) It’s really a pretty amazing hypothesis that draws on multiple different data points. Not shown in the video is what happens next. Had his theory been affirmed as correct (which in this case it isn’t), the example of a battery powered shoe with a USB port would have been “assimilated,” strengthening his existing knowledge of electronic devices. Presuming mom provides some explanation about store security tags, however, our little scientist will be disproven - forcing him to “accommodate” within his existing schema to take the existence of a new object into account. Either way, knowledge is being constructed. What an impressive little guy! 🧠 Have you noticed your children test their theories about the world? If so how? 🎥 hannahs_journeys IGshow more

In the earliest Mesopotamian creation accounts, after the departure... of the Anunnaki and in the aftermath of the Great Flood, a different group enters the story. The Apkallu, led by Oannes, are said to emerge from the waters of the Persian Gulf and begin teaching humanity the foundations of civilization including writing, agriculture, law, architecture, and sacred knowledge. This was at a moment when human society was super fragile and only beginning again. This raises a set of unresolved questions that the texts themselves never fully answer. Were the Apkallu NHI associated with the deep, possessing an unusual empathy for early humanity? Were they human survivors of a far more advanced pre flood culture, passing on retained knowledge to a diminished population? Or do these accounts describe something else entirely, an interaction that does not fit into modern categories of myth, history, or even speculation? What do you think?show more

[Graph Convolutional Network] by hand ✍️ Graph Convolutional Networks... (GCNs), introduced by Thomas Kipf and Max Welling in 2017, have emerged as a powerful tool in the analysis and interpretation of data structured as graphs. This exercise demonstrates how GCN works in a simple application: binary classification. -- Goal -- Predict if a node in a graph is X. -- Architecture -- 🟪 Graph Convolutional Network (GCN) 1. GCN1(4,3) 2. GCN2(3,3) 🟦 Fully Connected Network (FCN) 1. Linear1(3,5) 2. ReLU 3. Linear2(5,1) 4. Sigmoid Simplications: • Adjacent matrices are not normalized. • ReLU is applied to messages directly. -- Walkthrough -- [1] Given ↳ A graph with five nodes A, B, C, D, E [2] 🟩 Adjacency Matrix: Neighbors ↳ Add 1 for each edge to neighbors ↳ Repeat in both directions (e.g., A->C, C->A) ↳ Repeat for both GCN layers [3] 🟩 Adjacency Matrix: Self ↳ Add 1's for each self loop ↳ Equivalent to adding the identity matrix ↳ Repeat for both GCN layers [4] 🟪 GCN1: Messages ↳ Multiply the node embeddings 🟨 with weights and biases ↳ Apply ReLU (negatives → 0) ↳ The result is one message per node [5] 🟪 GCN1: Pooling ↳ Multiply the messages with the adjacent matrix ↳ The purpose is the pool messages from each node's neighbors as well as from the node itself. ↳ The result is a new feature per node [6] 🟪 GCN1: Visualize ↳ For node 1, visualize how messages are pooled to obtain a new feature for better understanding ↳ [3,0,1] + [1,0,0] = [4,0,1] [7] 🟪 GCN2: Messages ↳ Multiply the node features with weights and biases ↳ Apply ReLU (negatives → 0) ↳ The result is one message per node [8] 🟪 GCN2: Pooling ↳ Multiply the messages with the adjacent matrix ↳ The result is a new feature per node [9] 🟪 GCN2: Visualize ↳ For node 3, visualize how messages are pooled to obtain a new feature for better understanding ↳ [1,2,4] + [1,3,5] + [0,0,1] = [2,5,10] [10] 🟦 FCN: Linear 1 + ReLU ↳ Multiply node features with weights and biases ↳ Apply ReLU (negatives → 0) ↳ The result is a new feature per node ↳ Unlike in GCN layers, no messages from other nodes are included. [11] 🟦 FCN: Linear 2 ↳ Multiply node features with weights and biases [12] 🟦 FCN: Sigmoid ↳ Apply the Sigmoid activation function ↳ The purpose is to obtain a probability value for each node ↳ One way to calculate Sigmoid by hand ✍️ is to use the approximation below: • >= 3 → 1 • 0 → 0.5 • <= -3 → 0 -- Outputs -- A: 0 (Very unlikely) B: 1 (Very likely) C: 1 (Very likely) D: 1 (Very likely) E: 0.5 (Neutral)show more

🔥 𝐃𝐞𝐯 𝐔𝐩𝐝𝐚𝐭𝐞 – 𝐕𝐚𝐫𝐬𝐢𝐭𝐲 𝐇𝐢𝐠𝐡 𝐒𝐜𝐡𝐨𝐨𝐥 𝐅𝐨𝐨𝐭𝐛𝐚𝐥𝐥 What’s... new 👇 🎥 𝐌𝐨𝐭𝐢𝐨𝐧 𝐂𝐚𝐩𝐭𝐮𝐫𝐞 • New mocap session with our DB to capture swats, interceptions, and juke moves • Fresh animations now feeding into gameplay refinement 🎨 𝐓𝐞𝐚𝐦 𝐋𝐨𝐠𝐨𝐬 • First batch of 48 logo options ready for custom teams • If you use these instead of uploading your own, you can swap colors freely 🏈 𝟕𝐨𝐧𝟕 𝐆𝐚𝐦𝐞𝐩𝐥𝐚𝐲 • Full gameplay loop in place: team select ➝ play selection ➝ down management ➝ possession changes • This will be included in the December 7on7 alpha playtest • Varsity remains an 11v11 game, but 7on7 focus helps sharpen core QB/WR/DB gameplay while line play is still in development ❄️ 𝐖𝐢𝐧𝐭𝐞𝐫 𝐏𝐥𝐚𝐲𝐭𝐞𝐬𝐭 • Early 7on7 gameplay test • Multi-season Dynasty (sim only) • Coach schemes & tendencies • Community File Share server test 🗓️ Patreon signups: Nov 14 – Dec 19 🕹️ Playtest: Dec 20 – Jan 4 👉 Find out more: #VarsityVideoGame #HighSchoolFootball #7on7Footballshow more

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base... idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.show more

introducing a new, very fun, LLM benchmark- the Game-of-Life... Bench! the rules are simple: given an 8x8 grid following Conway's game of life rules, the goal is to create an initial pattern with at most 32 cells that can last the longest number of turns before dying/repeating. some results to highlight (with caveats detailed below): - gpt 5.1 lasts the longest with a 106 step run - claude models are really bad at this! they refuse to reason about this task and score < 25 points - deepseek r1 is the best open model with 102 steps. why? because i wanted to create a benchmark that has (i think) no practicality, but is still fun to look at, cheap, and still measures something interesting. i also am a big fan of the game of life. its absurdly simple rules leading to intractability is extremely cool to me. also, i saw a lot of work with LLMs trying to "predict" the next state in Conway's game of life, I think game-of-life bench is more fun because it's pretty open ended and only asks the LLM for the initial state. I also think this could be an RL env? but idk why you would ever train on this task haha i don't think this is a "serious" benchmark because it doesnt measure anything practical, but i still think it's a hard benchmark exactly because you can't predict what happens with your initial state many turns into the future; this is why i was initially expecting all LLMs to be bad at it, but turns out, some are clearly better than the others (the ordering may surprise you!) reminder: this is still a work-in-progress; (1) i am gpu-poor so could only do 10 runs for each model, even though total running cost is relatively low. maybe with some more credits i can run more seeds for each model. (2) i handpicked models which i think are at the frontier right now, plus some others that were on my mind. so, if you'd like to see a model on here, let me know. (3) i currently only do an 8x8 grid because i thought that by itself would be pretty hard for current LLMs, but of course we can increase grid sizes! (4) the coolest thing is, i dont think we can calculate the max possible number of states (yay undecidability!) you can go without repeating, so this is essentially a no-ceiling task, which is pretty cool! again, i did this mostly out of a desire to make LLMs do something fun. if this keeps me entertained for a few more days, i'd likely release a blog post on it. if it keeps me entertained for a week (and someone sponsors me), i'll put more work into it :P lastly, this is fully open sourced, so feel free to run this on your own!show more

💥 Building the future in DePIN? Applications for DePIN... Base Camp are open! In partnership with 1kx & peaq, we’re looking for the brightest founders to accelerate DePIN’s growth. Take the leap with Outlier Ventures, the world's leading Web3 accelerator. Why apply now? 🧠 Go-to-market strategies that scale → Learn proven frameworks from top DePIN startups 💰 Up to $200k investment → Backed by 1kx to fuel your vision 🌍 Real-world impact → Build what matters with trusted partners like peaq 🤝 Tailored mentorship → Receive hands-on guidance from Web3 experts + leaders 🎓 Tech + ecosystem insights → Navigate decentralized infra & the Post Web through an unparalleled lens Apply Now. ⌛️Deadline: Mid-February This accelerator isn’t just about building a product. It’s a Post Web Verified program focused on shaping the future of a decentralized, secure, & adaptive internet. ↳ Learn more:show more

Predicting the next word "only" is sufficient for language... models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.show more

Most chiral molecules arise from carbons being bonded to... 4 different atoms, which are called sterocenters. The makes the molecule have a different mirror image that cannot arise from simple rotation. But, you can have chiral molecules not from stereocenters. You can have chirality that doesn't come from a single point in the molecule. It comes from some global property. The classic example is helicene, which doesn't have any stereocenters, but has chirality because of hits helical structure. This means you cannot capture this molecule with a graph, and thus SMILES or a string representation cannot capture this. Of course natural language comes to the rescue (just say in words if it's left-handed or right-handed helix), but it's an interesting failure mode for viewing molecules as just a graph. Another example of a molecule with helical chirality is DNA. DNA is actually chiral in two ways, which is kind of confusing. It has both helical structure and stereocenters. You won't find the stereocenters ever flipped, but left-handed helical DNA can exist (called Z-DNA). Interestingly, making the flipped stereocenter of DNA could be part of an entire mirror organism (mirror RNA, DNA, AAs, sugars) that would then be potentially invisible to our immune systems. This has been recently proposed as a "mechanism" for how a runaway AI system could cause harm to Earth. I find it to be a pretty tedious and difficult way to cause harm, but it is intellectually cool. Anyway - this came up in a PhD defense and I have a lot of arcane knowledge about this I wanted to dump.show more

A little over a year ago, was just a... spark of an idea. Today, I’m blown away by what our team and community have built together. We’ve shipped a full-blown decentralized cloud stack—Ray, Kubernetes, Bare Metal, CaaS—with VMs and Deployment APIs on the horizon. It’s now a real contender alongside the biggest players out there. Over 300K GPUs have powered this network, with 6K+ active today and 5K+ hooked up through SuperAgg APIs. Our backbone is rock-solid and growing stronger every single day. IO Intelligence is live, serving up top open-source models and in-house tool agents, already handling 3B+ tokens a month. RAG is up and running, and agentic workflows are next in line. We’ve delivered $14M+ in compute, and the future is already fueled by 1K+ H200s and 800+ H100s serving enterprise-grade workloads. This is just the beginning—step one of a thousand. Grateful for this community and what’s to come. Let’s keep beaming forward. 🚀show more

⚡️ We are excited to introduce Rush Games -... a new platform that combines onchain gaming, mobile, social media and AI in innovative ways. 🎮 One of the key features we are most excited about is Rush Genie 🧞‍♂️, an AI agent trained on game development and the Beyond Network SDK, which will allow users to create their own mini-games without any coding knowledge. We believe this will open up new possibilities for creative game design. 🧩 With Rush, not only can you play a variety of engaging games, but you'll also have the opportunity to be rewarded for your creativity. But that's not all - we are integrating social features to take gameplay to the next level: 🆚 Connect with friends and challenge them head-to-head 🌐 Leverage decentralized social graphs for personalized, interconnected gaming experiences 💰 NFT holders will enjoy special perks like earning multipliers The $Bull token will be deeply integrated into the Rush Games ecosystem: 🪙 Spend $Bull to access Rush Genie and supercharge your game creation 🛍️ Use $Bull for in-game assets, lucky spins, draws, and raffles directly from Telegram and Farcaster on Base 🔒 Stake $Bull tokens to earn multipliers on your rewards 🔥 100% of revenues generated will be used to buy back and burn $Bull, driving sustainable value We are preparing to launch a selection of new titles that showcase the potential of on-chain gaming. Rush games beta along with our first game NetGains goes live on 25.01.25 ⚡️ Stay tuned for more details. The future of on-chain gaming is bright with #RushGames by #Bullieverse $Bullshow more

Valthos builds next-generation biodefense. Of all AI applications, biotechnology... has the highest upside and most catastrophic downside. Heroes at the frontlines of biodefense are working every day to protect the world against the worst case. But the pace of biotech is against them: more powerful methods to design biological systems, with near-universal access, open up an increasing surface area of threats. In this new world, the only way forward is to be faster. So we set out to build the tech stack for biodefense. Our team of computational biologists and software engineers applies frontier AI to identify biological threats and update medical countermeasures in real-time. We are backed by $30M from OpenAI, Lux Capital, Founders Fund and others including Definition. We are actively hiring engineers to join in the mission - if that sounds like you, get in touch.show more

"You're asking me how a watch works... for now,... let's just keep an eye on the time." It's a great line because it's not really about watches. On the surface, she's asking for a detailed explanation of something really complex. His response is essentially: "The explanation is complicated, and understanding every mechanism isn't necessary right now. Focus on the outcome, not the internals." The watch metaphor works because everyone understands the difference between: - Knowing what time it is. - Knowing how a watch actually works. Most people can use a watch perfectly well without understanding gears, escapements, balance wheels, or quartz crystals. For young people, apprentices, junior engineers, new managers, or anyone entering a new field, there's a deeper lesson: - Expertise comes in layers When you're new, you often want the entire mental model immediately. You ask: - Why are we doing it this way? - What does every part do? - What are all the dependencies? - What happens under every possible condition? Those are good questions. But sometimes the answer would require six months of background knowledge to make sense. It's great to be curious, as long as sometimes you're willing to accept that the answer is "I can't explain it all to you right now." An experienced person may effectively be saying: "You're asking a valid question, but you're asking it several chapters before the book has introduced the necessary concepts." That can be hard when you're young and driven!show more