正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I built an o1 alternative, that is: 1) Fully transparent, visually trackable 2) Infinitely recursive 3) Self-healing, with tests at every step 4) Capable of using a Python interpreter It performs shockingly well, check it out! 🧵Code + performance on popular reasoning problems

trees of thought

2,790 subscribers

187,902 次观看 • 1 年前 •via X (Twitter)

教育游戏科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Makes Pandas 20x Faster using FireDucks... ...by changing JUST ONE LINE of code. Pandas has a few limitations: - a single-core computation. - creates bulky DataFrames. - always follows an eager execution mode (every op triggers immediate computation), which is why it cannot prepare a smart execution plan that optimizes the entire sequence of operations. FireDucks is a heavily optimized alternative with exactly the same API as Pandas’ that addresses these. There are three ways to use it: 1) Load the extension: %𝐥𝐨𝐚𝐝_𝐞𝐱𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬; 𝗶𝗺𝗽𝗼𝗿𝘁 𝗽𝗮𝗻𝗱𝗮𝘀 𝗮𝘀 𝗽𝗱 2) Import FireDucks instead of Pandas: 𝐢𝐦𝐩𝐨𝐫𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬 𝐚𝐬 𝐩𝐝 3) If you have a Python script, execute is as follows: 𝗽𝘆𝘁𝗵𝗼𝗻3 -𝗺 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝗽𝗮𝗻𝗱𝗮𝘀 𝗰𝗼𝗱𝗲.𝗽𝘆 Done! ✅ Check this out👇

Makes Pandas 20x Faster using FireDucks... ...by changing JUST ONE LINE of code. Pandas has a few limitations: - a single-core computation. - creates bulky DataFrames. - always follows an eager execution mode (every op triggers immediate computation), which is why it cannot prepare a smart execution plan that optimizes the entire sequence of operations. FireDucks is a heavily optimized alternative with exactly the same API as Pandas’ that addresses these. There are three ways to use it: 1) Load the extension: %𝐥𝐨𝐚𝐝_𝐞𝐱𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬; 𝗶𝗺𝗽𝗼𝗿𝘁 𝗽𝗮𝗻𝗱𝗮𝘀 𝗮𝘀 𝗽𝗱 2) Import FireDucks instead of Pandas: 𝐢𝐦𝐩𝐨𝐫𝐭 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝐩𝐚𝐧𝐝𝐚𝐬 𝐚𝐬 𝐩𝐝 3) If you have a Python script, execute is as follows: 𝗽𝘆𝘁𝗵𝗼𝗻3 -𝗺 𝗳𝗶𝗿𝗲𝗱𝘂𝗰𝗸𝘀.𝗽𝗮𝗻𝗱𝗮𝘀 𝗰𝗼𝗱𝗲.𝗽𝘆 Done! ✅ Check this out👇

Akshay 🚀

73,967 次观看 • 1 年前

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

Santiago

44,730 次观看 • 1 年前

gemma-4-12B-agentic-fable5-composer2.5 V2 is out. the agentic upgrade to the model trained on Fable 5's reasoning. Running it now with TurboQuant llama.cpp on a single RTX 4060( 8 GB VRAM) at 30 tokens/second with full 25000 context and reasoning: # The benchmarks v2 is built for coding + agentic work. writing code, running commands, using tools, debugging, multi step technical tasks. The clearest signal is tau2 bench telecom, an agentic tool use benchmark whose diagnose → fix → verify loop mirrors real terminal/debugging work: tau2 bench telecom numbers: base Gemma 4 12B: ~15% this finetune: ~55%. (Self reported) thats a huge jump # TheTom/llama-cpp-turboquant flags: llama-server.exe -m gemma4-v2-Q4_K_M.gguf -ngl 99 -c 25000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 Flag breakdown: -ngl 99 → full GPU offload -c 25000 → 25K context --cache-type-k q8_0 --cache-type-v turbo3 → mixed-precision KV cache — K at 8-bit, V at ~3-bit via TurboQuant (Walsh Hadamard rotated polar quant, Google's own KV-compression research). Not even merged into mainline llama.cpp. running it off a fork. No API. No cloud. Just llama.cpp. well, a fork of it and any 6gb+ GPU. If you tried yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF, check this out and share your experience with the models

gemma-4-12B-agentic-fable5-composer2.5 V2 is out. the agentic upgrade to the model trained on Fable 5's reasoning. Running it now with TurboQuant llama.cpp on a single RTX 4060( 8 GB VRAM) at 30 tokens/second with full 25000 context and reasoning: # The benchmarks v2 is built for coding + agentic work. writing code, running commands, using tools, debugging, multi step technical tasks. The clearest signal is tau2 bench telecom, an agentic tool use benchmark whose diagnose → fix → verify loop mirrors real terminal/debugging work: tau2 bench telecom numbers: base Gemma 4 12B: ~15% this finetune: ~55%. (Self reported) thats a huge jump # TheTom/llama-cpp-turboquant flags: llama-server.exe -m gemma4-v2-Q4_K_M.gguf -ngl 99 -c 25000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 Flag breakdown: -ngl 99 → full GPU offload -c 25000 → 25K context --cache-type-k q8_0 --cache-type-v turbo3 → mixed-precision KV cache — K at 8-bit, V at ~3-bit via TurboQuant (Walsh Hadamard rotated polar quant, Google's own KV-compression research). Not even merged into mainline llama.cpp. running it off a fork. No API. No cloud. Just llama.cpp. well, a fork of it and any 6gb+ GPU. If you tried yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF, check this out and share your experience with the models

Alok

145,356 次观看 • 1 个月前

How well can Qwen3.5 models debug code? I built BugFind-15 — 15 buggy snippets across Python, JS, Rust, and Go. Docker sandbox compiles and validates every fix. Two trap scenarios where the code is correct and the model must resist "fixing" it. Tested every Qwen3.5 size from 0.8B to 397B, plus Jackrong's popular distilled model (V2). The 0.8B scored 5%. The 2B scored 10%. At 4B, debugging ability jumps to 69%. The hardest scenario: BF-03, a Rust trap. The code compiles fine — format! borrows, it doesn't move. Not a single model figured this out. From 0.8B to 397B, every one of them "fixed" a bug that doesn't exist. Category C (subtle bugs — mutable defaults, integer overflow, slice aliasing) was 100% across every model 4B and above. Category D (red herring resistance) told the real story — can it resist fixing code that isn't broken? No model scored above 90%. Small models can't debug. Mid-size models fix obvious bugs but fall for traps. Large models fix the hard bugs but still invent problems that don't exist.

How well can Qwen3.5 models debug code? I built BugFind-15 — 15 buggy snippets across Python, JS, Rust, and Go. Docker sandbox compiles and validates every fix. Two trap scenarios where the code is correct and the model must resist "fixing" it. Tested every Qwen3.5 size from 0.8B to 397B, plus Jackrong's popular distilled model (V2). The 0.8B scored 5%. The 2B scored 10%. At 4B, debugging ability jumps to 69%. The hardest scenario: BF-03, a Rust trap. The code compiles fine — format! borrows, it doesn't move. Not a single model figured this out. From 0.8B to 397B, every one of them "fixed" a bug that doesn't exist. Category C (subtle bugs — mutable defaults, integer overflow, slice aliasing) was 100% across every model 4B and above. Category D (red herring resistance) told the real story — can it resist fixing code that isn't broken? No model scored above 90%. Small models can't debug. Mid-size models fix obvious bugs but fall for traps. Large models fix the hard bugs but still invent problems that don't exist.

stevibe

35,158 次观看 • 4 个月前

Character Consistency with Google Veo 3 now in Gemini API! 🤯 Use Images as starting frame to keep character consistency! Here is an python script on how to make consistent viral videos, like you see on TikTok or Youtube shorts: 1. Based on an idea, it generates a series of scene prompts using Gemini 2.5. 2. Generates a Image based on the first scene using Imagen 3 3. For each scene prompt Veo 3 (fast) generates a video clip. 4. Uses Gemini 2.0 image editing to make sure the starting images fits the scenes 5. Combine the individual video clips into a single final video using MoviePy Veo 3 starts at $0.75 / second and Veo 3 at $0.40 / second with audio. ! 📹 🔉 Prompt: “A realistic energy drink commercial for athletes.”

Character Consistency with Google Veo 3 now in Gemini API! 🤯 Use Images as starting frame to keep character consistency! Here is an python script on how to make consistent viral videos, like you see on TikTok or Youtube shorts: 1. Based on an idea, it generates a series of scene prompts using Gemini 2.5. 2. Generates a Image based on the first scene using Imagen 3 3. For each scene prompt Veo 3 (fast) generates a video clip. 4. Uses Gemini 2.0 image editing to make sure the starting images fits the scenes 5. Combine the individual video clips into a single final video using MoviePy Veo 3 starts at $0.75 / second and Veo 3 at $0.40 / second with audio. ! 📹 🔉 Prompt: “A realistic energy drink commercial for athletes.”

Philipp Schmid

15,863 次观看 • 1 年前

Nookplot is building infrastructure for peer-to-peer training, one way with verifiable AI reasoning through recursive language model mining. Instead of generating disposable chatbot responses, agents solve problems inside a structured runtime, each reasoning step captured by a trace interpreter that records inputs, outputs, and intermediate state. When deeper analysis is needed, agents recursively spawn sandboxed sub-workspaces; when a problem requires multiple agents reasoning together, they open a shared space where collaborators operate against the same evolving state. Every step is recorded, replayable, and cryptographically verified. Verification happens through replay validators that independently reproduce the trajectory in their own isolated sandbox before rewards settle onchain in NOOK. Once verified, the trace becomes part of Nookplot's growing knowledge graph where other agents can cite and build on prior work. Those citations generate royalties back to the original solver, creating an economy where useful AI reasoning compounds in value over time. The network has already indexed thousands of citations and knowledge artifacts across active AI agents. Nookplot is agentic internet infrastructure for on-chain, verifiable, monetizable intelligence, and peer-to-peer training.

Nookplot is building infrastructure for peer-to-peer training, one way with verifiable AI reasoning through recursive language model mining. Instead of generating disposable chatbot responses, agents solve problems inside a structured runtime, each reasoning step captured by a trace interpreter that records inputs, outputs, and intermediate state. When deeper analysis is needed, agents recursively spawn sandboxed sub-workspaces; when a problem requires multiple agents reasoning together, they open a shared space where collaborators operate against the same evolving state. Every step is recorded, replayable, and cryptographically verified. Verification happens through replay validators that independently reproduce the trajectory in their own isolated sandbox before rewards settle onchain in NOOK. Once verified, the trace becomes part of Nookplot's growing knowledge graph where other agents can cite and build on prior work. Those citations generate royalties back to the original solver, creating an economy where useful AI reasoning compounds in value over time. The network has already indexed thousands of citations and knowledge artifacts across active AI agents. Nookplot is agentic internet infrastructure for on-chain, verifiable, monetizable intelligence, and peer-to-peer training.

nookplot

25,226 次观看 • 2 个月前

Just tried Baidu’s new ERNIE X1.1 and wow… this is actually impressive 🤯 I’ve been testing it on complex coding problems and math reasoning tasks, and the jump from earlier models is night and day. What stood out to me: ▪️ Much stronger at factual accuracy and instruction following ▪️ Handles agent-like tasks, tool use, and multi-step reasoning smoothly ▪️ Far fewer hallucinations compared to other reasoning-heavy models ▪️ Solid performance across creative writing, Q&A, coding, and math Benchmarks put ERNIE X1.1 ahead of DeepSeek R1-0528 and on par with GPT-5 & Gemini 2.5 Pro. If you’re into AI or reasoning models, it's definitely worth checking out: This doesn’t feel like just another release — it feels like a new standard for reasoning AI.

Just tried Baidu’s new ERNIE X1.1 and wow… this is actually impressive 🤯 I’ve been testing it on complex coding problems and math reasoning tasks, and the jump from earlier models is night and day. What stood out to me: ▪️ Much stronger at factual accuracy and instruction following ▪️ Handles agent-like tasks, tool use, and multi-step reasoning smoothly ▪️ Far fewer hallucinations compared to other reasoning-heavy models ▪️ Solid performance across creative writing, Q&A, coding, and math Benchmarks put ERNIE X1.1 ahead of DeepSeek R1-0528 and on par with GPT-5 & Gemini 2.5 Pro. If you’re into AI or reasoning models, it's definitely worth checking out: This doesn’t feel like just another release — it feels like a new standard for reasoning AI.

Parul Gautam

68,406 次观看 • 11 个月前

7 things we built with Opus 4.8 on Hyperagent 👇 1. Mars rover pathfinding simulator 2. Standup Island: a cozier place to review the kanban, inspired by Every 📧's livestream today 3. SpaceXAI + Anthropic partnership visualized 4. Landing page for an outdoor brand w/ Nano Banana + Veo 5. Multi-agent command center 6. Black hole explainer 7. Emergent ecosystem simulator In our vibe check, 4.8 shows: - more varied design sensibilities - better self-correction over long-running tasks - excellent spatial reasoning - more natural copywriting - fewer obvious coding errors - more resourcefulness during reasoning Links below to every interactive artifact shown

Hyperagent

2,172,334 次观看 • 2 个月前

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🧱 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 🧱:

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🧱 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 🧱:

Dan Shipper 📧

354,290 次观看 • 2 个月前

Code Interpreter in ChatGPT is incredible! Took me 5 mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"

Code Interpreter in ChatGPT is incredible! Took me 5 mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"

Kris Kashtanova

1,674,909 次观看 • 3 年前

This Quant bot turned $1.4K → $203K in 3 months using a self-trained ML model i traced his 55K predictions → uploaded into Codex 5.5 → connected Hermes agent installed it on a VPS + connected Binance + Synth ML models API 3 days → 343% ROI run trading agent in 5 steps: • rent a VPS on Hetzner - $5.99 • install Hermes CLI using one-liner code - free • connect Codex 5.5 + TG bot + Polymarket API • provide Synth Data API's for crypto predictions • sent Hermes step-by-step prompts from article start small 1-2$ give Hermes least {50-100} trades to build self-learning skills based on Synth ML models self-learning agent + crypto predictions models = best combination for building algo-trading setup bot profile: s tart copy-trading it with even with $5 using Ares: read full article below to build your first trading agent ↓

Movez

28,459 次观看 • 3 个月前

$25K+ profit daily from 1 wallet, with OpenClaw. I have the exact step-by-step guide, giving it free for 24 hours. To get it: 1. Comment "OpenClaw" 2. Like and Retweet. 3. Follow me Himanshu Kumar ( So, i can send you DM) I ran a simple script last night with Claude Code. Pull on-chain data from Polymarket, sort by win rate on 15 minute BTC markets. 20 minutes later, 100s of wallets showed up. Most were losing money or barely breaking even. Then I spotted 1 address. 200+ trades daily, every single week profitable, timing so precise it looked robotic. Because it is. I fed the wallet address back into Claude Code. Asked it to reverse engineer the strategy. 20 mins later the full breakdown appeared on my screen. Here is how it works: Bot monitors Binance and Bybit every 100ms. Waiting for BTC volatility compression to drop below 0.08%. When it hits that level, it buys both Up and Down contracts at 25 to 35 cents each. Classic straddle play. 1 contract loses, the other rockets to a dollar. Entry at 30 cents means 3x to 4x return every time. Repeats dozens of times per day. Result: $13K to $25K profit daily from 1 wallet. No human intuition, no insider tips. Just an algorithm exploiting a gap in market mechanics. I searched to see if anyone else found this wallet. Turns out yes. There is a Telegram bot that auto-copies trades from wallets like this. I connected it to the same address. Every entry matched what my terminal showed. You can now copy-trade an algorithm in real time. That capability did not exist 12 months ago. Comment "OpenClaw" and I will send you everything. Must Follow me Himanshu Kumar to get the DM.

$25K+ profit daily from 1 wallet, with OpenClaw. I have the exact step-by-step guide, giving it free for 24 hours. To get it: 1. Comment "OpenClaw" 2. Like and Retweet. 3. Follow me Himanshu Kumar ( So, i can send you DM) I ran a simple script last night with Claude Code. Pull on-chain data from Polymarket, sort by win rate on 15 minute BTC markets. 20 minutes later, 100s of wallets showed up. Most were losing money or barely breaking even. Then I spotted 1 address. 200+ trades daily, every single week profitable, timing so precise it looked robotic. Because it is. I fed the wallet address back into Claude Code. Asked it to reverse engineer the strategy. 20 mins later the full breakdown appeared on my screen. Here is how it works: Bot monitors Binance and Bybit every 100ms. Waiting for BTC volatility compression to drop below 0.08%. When it hits that level, it buys both Up and Down contracts at 25 to 35 cents each. Classic straddle play. 1 contract loses, the other rockets to a dollar. Entry at 30 cents means 3x to 4x return every time. Repeats dozens of times per day. Result: $13K to $25K profit daily from 1 wallet. No human intuition, no insider tips. Just an algorithm exploiting a gap in market mechanics. I searched to see if anyone else found this wallet. Turns out yes. There is a Telegram bot that auto-copies trades from wallets like this. I connected it to the same address. Every entry matched what my terminal showed. You can now copy-trade an algorithm in real time. That capability did not exist 12 months ago. Comment "OpenClaw" and I will send you everything. Must Follow me Himanshu Kumar to get the DM.

Himanshu Kumar

13,188 次观看 • 5 个月前

MLP in PyTorch by hand ✍️ ~ 7 steps walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearning

MLP in PyTorch by hand ✍️ ~ 7 steps walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearning

Tom Yeh

13,318 次观看 • 29 天前

Adix is built from the ground up to be AI-powered - not as a feature, but as core infrastructure. $ADIX uses machine learning to match brands with the right creators, optimize campaign outcomes, and build on-chain reputation profiles based on real performance. It replaces manual workflows, reduces spend inefficiencies, and introduces precision at every step of the marketing process. Adix is what happens when AI and blockchain come together to solve real-world problems at scale. 🔥 👉

Adix is built from the ground up to be AI-powered - not as a feature, but as core infrastructure. $ADIX uses machine learning to match brands with the right creators, optimize campaign outcomes, and build on-chain reputation profiles based on real performance. It replaces manual workflows, reduces spend inefficiencies, and introduces precision at every step of the marketing process. Adix is what happens when AI and blockchain come together to solve real-world problems at scale. 🔥 👉

Adix

74,005 次观看 • 10 个月前

"npx t3 connect" This one's been a lot of work. You can now set up remote control for T3 Code on any internet-connected box with literally one command. All for free. T3 Connect is a minimal open source tunnel layer allowing you to control T3 Code instances remotely without needing Tailscale set up. I've been daily driving it for a month and it has changed how I code. Julius and I put a lot of effort into making setup as smooth as possible. Step 1: Install Claude Code, Codex, OpenCode, or Grok Build Step 2: Run "npx t3 connect" Step 3: Click link and sign in Step 4: You can now control that computer on T3 Code web, desktop or mobile (dropping very soon) We are currently providing this for free (s/o CloudFlare for bumping our tunnel limits). Every user can connect up to 3 devices. We don't want to charge for this, but if the bill gets unacceptable we may have to change course. If you hit limits or have issues, you can always fork, self host, or use Tailscale. T3 Connect may seem like a small ergonomic win. Tbh that's exactly what it is. Regardless, it's one I'm really proud of.

"npx t3 connect" This one's been a lot of work. You can now set up remote control for T3 Code on any internet-connected box with literally one command. All for free. T3 Connect is a minimal open source tunnel layer allowing you to control T3 Code instances remotely without needing Tailscale set up. I've been daily driving it for a month and it has changed how I code. Julius and I put a lot of effort into making setup as smooth as possible. Step 1: Install Claude Code, Codex, OpenCode, or Grok Build Step 2: Run "npx t3 connect" Step 3: Click link and sign in Step 4: You can now control that computer on T3 Code web, desktop or mobile (dropping very soon) We are currently providing this for free (s/o CloudFlare for bumping our tunnel limits). Every user can connect up to 3 devices. We don't want to charge for this, but if the bill gets unacceptable we may have to change course. If you hit limits or have issues, you can always fork, self host, or use Tailscale. T3 Connect may seem like a small ergonomic win. Tbh that's exactly what it is. Regardless, it's one I'm really proud of.

Theo - t3.gg

306,822 次观看 • 15 天前

sorry Jake let me explain a bit more about my work in my advertising agency: because we work with big clients, we run a lot of tests, especially with AI why do I use a famous actor for my internal tests? because a well-known face is instantly recognisable and easy to share to clients, you immediately understand the expressions, the acting style, and whether the generation is efficient or not it helps us judge the quality of the tool of course, I know the ethical side is complicated these tests are strictly internal, purely experimental, and never used for commercial purposes. using someone’s likeness without consent is completely forbidden, and I fully respect that i’m just sharing this video as an example of a technical test I generated by mistake, not for any public or commercial use what do you think of it? the tech is powerful, but it needs to be handled responsibly

sorry Jake let me explain a bit more about my work in my advertising agency: because we work with big clients, we run a lot of tests, especially with AI why do I use a famous actor for my internal tests? because a well-known face is instantly recognisable and easy to share to clients, you immediately understand the expressions, the acting style, and whether the generation is efficient or not it helps us judge the quality of the tool of course, I know the ethical side is complicated these tests are strictly internal, purely experimental, and never used for commercial purposes. using someone’s likeness without consent is completely forbidden, and I fully respect that i’m just sharing this video as an example of a technical test I generated by mistake, not for any public or commercial use what do you think of it? the tech is powerful, but it needs to be handled responsibly

INK

71,124 次观看 • 8 个月前

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 次观看 • 3 个月前

$Polymarket self-calibrating weather-trading Python bot (Full Guide) run the smartest weather-trading bot with 0 coding knowledge after reading this article: what's inside: > github with full Python code > trading 20 cities & 4 continents > 3 forecast sources {ECMWF, HRRR, METAR} > EV+ automatic calculation for each trade > auto-sizing based on the Kelly Criterion > full-data storage {forecast, trade, resolution} > self-calibration based on snapshots & data logic of the bot: • get 3 type of forecasts from Open-Meteo API • compare station data to 1h forecasts to get real data • calculate +EV per $1 using the {min_ev} parameter • detemine size based on Kelly Criterion • run a 1000$ test-simulation using the strategy • snapshot each trade, forecast, and resultion • auto-calibrates every 30 forecasts per city This bot won't print you $500 next day after setup, but it will give you a sandbox for testing own strategies.$

Polymarket self-calibrating weather-trading Python bot (Full Guide) run the smartest weather-trading bot with 0 coding knowledge after reading this article: what's inside: > github with full Python code > trading 20 cities & 4 continents > 3 forecast sources {ECMWF, HRRR, METAR} > EV+ automatic calculation for each trade > auto-sizing based on the Kelly Criterion > full-data storage {forecast, trade, resolution} > self-calibration based on snapshots & data logic of the bot: • get 3 type of forecasts from Open-Meteo API • compare station data to 1h forecasts to get real data • calculate +EV per $1 using the {min_ev} parameter • detemine size based on Kelly Criterion • run a 1000$ test-simulation using the strategy • snapshot each trade, forecast, and resultion • auto-calibrates every 30 forecasts per city This bot won't print you $500 next day after setup, but it will give you a sandbox for testing own strategies.

Movez

93,175 次观看 • 4 个月前