Загрузка видео...

Не удалось загрузить видео

На главную

THIS CHINESE DEVELOPER VISUALIZED WHAT 300 KIMI K2.6 AGENTS LOOK LIKE IN ACTION - AND IT LOOKS EXACTLY LIKE A BRAIN WORKING FOR YOU every line on screen is a connection firing in real time - hundreds of neurons across multiple layers, activations lighting up, signals passing through the...

noisyb0y1's profile picture

Noisy

20,867 subscribers

137,889 просмотров • 18 дней назад •via X (Twitter)

Наука и технологииФинансы
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system
1:28

THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system

Gipp 🦅

16,989 просмотров • 17 дней назад

A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the architecture, writes production code and ships for $150-300 in API costs while a traditional agency pays developers $4,800 for the exact same project. 300 parallel agents per run deliver 100+ files simultaneously - search, analysis, coding and writing all in parallel - and Obsidian visualizes the entire knowledge graph in real time while the agents work. A traditional agency with 10-15 people keeps 30% margin after salaries. He keeps 90% - $72,000 in monthly profit with $500 in overhead. By month 10 Kimi handles 80% of the technical work and he manages only strategy and client relationships - while Obsidian maps every project, every client and every agent in one graph that updates itself.
0:33

A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the architecture, writes production code and ships for $150-300 in API costs while a traditional agency pays developers $4,800 for the exact same project. 300 parallel agents per run deliver 100+ files simultaneously - search, analysis, coding and writing all in parallel - and Obsidian visualizes the entire knowledge graph in real time while the agents work. A traditional agency with 10-15 people keeps 30% margin after salaries. He keeps 90% - $72,000 in monthly profit with $500 in overhead. By month 10 Kimi handles 80% of the technical work and he manages only strategy and client relationships - while Obsidian maps every project, every client and every agent in one graph that updates itself.

Noisy

846,932 просмотров • 1 месяц назад

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!
0:41

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Avi Chawla

108,824 просмотров • 1 месяц назад

A security guard turned $900 into $187,000 on Polymarket. Guarded empty buildings for 10 years at $16/hour. One sleepless shift he built a BTC bot with Claude Opus 4.8. Never wrote a single line of code. I found his wallet. Reverse-engineered the entire system. Here is what he actually did. Gave Claude new Fable 5 two prompts at the start of his shift. Opus did not write the bot. It drew the blueprint: data, signals, backtest, risk, execution. Then handed that blueprint to a swarm of 300 agents. How it works: → Decompose: Claude Fable 5 breaks the goal into a task tree → Dispatch: 300 agents fan out (some pulling Binance data, some writing code, some backtesting 5 years of data) → Execute: 4,000 steps in one 14-hour run → Review: Claude Fable 5 reads it all back and kills whatever drifted The brain never wrote a line. The hands never made a call. By sunrise he had what a 6-engineer quant team ships in a quarter. A live BTC bot on Polymarket. Backtested. Risk-capped. Running 24/7. For 10 years he watched empty buildings. Now 300 agents watch the market while he sleeps. I rebuilt this exact system with Claude new Fable 5 You only need Claude + device + 1 hour to deploy. Giving this free for 24 hours. To get it: 1. Comment "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you
0:55

A security guard turned $900 into $187,000 on Polymarket. Guarded empty buildings for 10 years at $16/hour. One sleepless shift he built a BTC bot with Claude Opus 4.8. Never wrote a single line of code. I found his wallet. Reverse-engineered the entire system. Here is what he actually did. Gave Claude new Fable 5 two prompts at the start of his shift. Opus did not write the bot. It drew the blueprint: data, signals, backtest, risk, execution. Then handed that blueprint to a swarm of 300 agents. How it works: → Decompose: Claude Fable 5 breaks the goal into a task tree → Dispatch: 300 agents fan out (some pulling Binance data, some writing code, some backtesting 5 years of data) → Execute: 4,000 steps in one 14-hour run → Review: Claude Fable 5 reads it all back and kills whatever drifted The brain never wrote a line. The hands never made a call. By sunrise he had what a 6-engineer quant team ships in a quarter. A live BTC bot on Polymarket. Backtested. Risk-capped. Running 24/7. For 10 years he watched empty buildings. Now 300 agents watch the market while he sleeps. I rebuilt this exact system with Claude new Fable 5 You only need Claude + device + 1 hour to deploy. Giving this free for 24 hours. To get it: 1. Comment "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you

Himanshu Kumar

53,524 просмотров • 12 дней назад

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself
1:03

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself

Om Patel

695,260 просмотров • 2 месяцев назад

THIS IS ANDREJ KARPATHY'S OBSIDIAN VAULT : THE BRAIN ANTHROPIC JUST HIRED FOR MILLIONS This is every idea, every decision and every connection he's made over years of work, visualized in real time. Everything else gets lost. The pattern you noticed last March. The connection between two problems you solved a year apart. The idea that would've changed everything if you'd remembered it in the room. This system keeps all of it. Every note links to another. Every link becomes a path. Every path is a decision he can retrace in seconds while everyone else starts from zero. Thousands of nodes. Hundreds of live connections. Years of thinking that never decayed, never died in a Slack thread, never got buried in a meeting nobody remembers. The breakthroughs aren't luck. They're the system handing him back a link he made eighteen months ago and forgot he had. No team. No wiki. No standups. One person and a tool that remembers everything he can't. Most people open Obsidian and make three notes they never open again. He built an operating system for his own thinking. Anthropic just paid millions for the output - this is the machine that produced it.
22:22

THIS IS ANDREJ KARPATHY'S OBSIDIAN VAULT : THE BRAIN ANTHROPIC JUST HIRED FOR MILLIONS This is every idea, every decision and every connection he's made over years of work, visualized in real time. Everything else gets lost. The pattern you noticed last March. The connection between two problems you solved a year apart. The idea that would've changed everything if you'd remembered it in the room. This system keeps all of it. Every note links to another. Every link becomes a path. Every path is a decision he can retrace in seconds while everyone else starts from zero. Thousands of nodes. Hundreds of live connections. Years of thinking that never decayed, never died in a Slack thread, never got buried in a meeting nobody remembers. The breakthroughs aren't luck. They're the system handing him back a link he made eighteen months ago and forgot he had. No team. No wiki. No standups. One person and a tool that remembers everything he can't. Most people open Obsidian and make three notes they never open again. He built an operating system for his own thinking. Anthropic just paid millions for the output - this is the machine that produced it.

Avid

64,799 просмотров • 23 дней назад

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.
12:14

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Mnimiy

112,687 просмотров • 9 дней назад

THIS CHINESE DEVELOPER’S NEURAL NETWORK VISUALIZATION IS EXACTLY HOW YOUR OBSIDIAN VAULT SHOULD WORK every node connects to every other node and the whole thing gets smarter the more data flows through it, same way a real knowledge system should work but almost nobody builds it like that most people throw everything into folders and tags and call it a second brain but what they actually built is an archive that gets harder to use every month claude reads across everything you ever captured and finds the connection you need right when you need it here’s how to build the version that actually compounds ↓
0:32

THIS CHINESE DEVELOPER’S NEURAL NETWORK VISUALIZATION IS EXACTLY HOW YOUR OBSIDIAN VAULT SHOULD WORK every node connects to every other node and the whole thing gets smarter the more data flows through it, same way a real knowledge system should work but almost nobody builds it like that most people throw everything into folders and tags and call it a second brain but what they actually built is an archive that gets harder to use every month claude reads across everything you ever captured and finds the connection you need right when you need it here’s how to build the version that actually compounds ↓

leopardracer

229,882 просмотров • 24 дней назад

Chinese professor just revealed his development team - and it was 170 AI agents making every single company decision not humans, not managers, not consultants charging $500 an hour 170 artificial developers working in parallel, never sleeping, never asking for a raise, never going on vacation Kimi K2.6 runs all of them with one prompt and each one gets its own task what used to take an entire department two weeks now takes two hours and costs less than a cup of coffee and while most companies are still hiring people for these roles the ones who understood what's happening already quietly rebuilt everything this is what actually sits behind the growth of billion dollar companies right now full breakdown of how it works in the article below
0:21

Chinese professor just revealed his development team - and it was 170 AI agents making every single company decision not humans, not managers, not consultants charging $500 an hour 170 artificial developers working in parallel, never sleeping, never asking for a raise, never going on vacation Kimi K2.6 runs all of them with one prompt and each one gets its own task what used to take an entire department two weeks now takes two hours and costs less than a cup of coffee and while most companies are still hiring people for these roles the ones who understood what's happening already quietly rebuilt everything this is what actually sits behind the growth of billion dollar companies right now full breakdown of how it works in the article below

Sprytix

106,640 просмотров • 16 дней назад

A girl set up AI agents to run her business while she sleeps. By the time she wakes up, money has already moved. She built the system once. Took a few evenings. Now it runs without her. Here is what it looks like. An AI agent monitors trending topics 24 hours a day. Finds what people are searching for, what they are buying, what they need answered. Sends her a report every morning she barely reads anymore because the next agent already acted on it. Another agent writes the content. Product descriptions, emails, social posts, video scripts. Hundreds of them. Personalized. Published. Done before sunrise. A third agent handles customer messages. Answers questions, processes requests, follows up. Fluent. Fast. Never offline. She wakes up, checks the dashboard, sees what came in overnight. Last month: $23,000. The month before: $19,000. She is not a programmer. She did not write a single line of code. She described what she wanted in plain language and the agents figured out the rest. During the day she refines things. Adjusts. Thinks about where to point the system next. That is maybe an hour of her time. The other 23 hours the agents are working. Most people trade time for money. She traded one week of setup for a business that never clocks out. Save this before everyone realizes agents do not need a salary.
0:35

A girl set up AI agents to run her business while she sleeps. By the time she wakes up, money has already moved. She built the system once. Took a few evenings. Now it runs without her. Here is what it looks like. An AI agent monitors trending topics 24 hours a day. Finds what people are searching for, what they are buying, what they need answered. Sends her a report every morning she barely reads anymore because the next agent already acted on it. Another agent writes the content. Product descriptions, emails, social posts, video scripts. Hundreds of them. Personalized. Published. Done before sunrise. A third agent handles customer messages. Answers questions, processes requests, follows up. Fluent. Fast. Never offline. She wakes up, checks the dashboard, sees what came in overnight. Last month: $23,000. The month before: $19,000. She is not a programmer. She did not write a single line of code. She described what she wanted in plain language and the agents figured out the rest. During the day she refines things. Adjusts. Thinks about where to point the system next. That is maybe an hour of her time. The other 23 hours the agents are working. Most people trade time for money. She traded one week of setup for a business that never clocks out. Save this before everyone realizes agents do not need a salary.

Shelpid.WI3M

25,477 просмотров • 1 месяц назад

I pay Claude $20 a month. Most $TAO holders do too. There is a stack you can build in 15 minutes that fixes that completely. It runs on Bittensor. It costs $10. You do not write a single line of code. Here is how every AI chat product actually works under the hood. Three layers. Always three. The model. The brain. GPT, Claude, DeepSeek, Kimi, GLM. The inference layer. The GPU that runs the model when you hit send. The interface. The chat box you actually look at. ChatGPT and Claude bundle all three and hand you the result. You cannot change the model. You cannot change the inference. The interface is non-negotiable. Every prompt you type goes to a server run by a private company whose terms of service can quietly change next month. The anti-ChatGPT move is to pick each layer yourself. This is where $TAO comes in. Chutes is Subnet 64 on Bittensor. It is the inference layer. Open source models like DeepSeek, Kimi, GLM, and Llama get served by a global network of miner-operated GPUs. Validators score the output quality. The best inference wins the emissions. You hit send. A miner somewhere runs your prompt. You get the answer back. The TAO you hold is in part paying for the GPU you just used. The basic stack is one URL. chutes. ai/chat No account. No API key. No setup. Switch models mid-conversation. Web search built in. Image generation. File uploads. Free. The advanced stack is Chutes plus TypingMind. One-time license. No recurring fee. Plugins, agents, custom personas, a prompt library you build over months. Full model switching between Chutes, OpenAI, and Anthropic from the same window. Total cost: $10 a month to Chutes for inference. That $10 buys you $50 in actual usage. But here is the signal most people missed inside this story. Chutes ran a free tier until February. Then they killed it. Then they raised the minimum to $10 in May. Most people saw that as bad news. It is the opposite. Free things on the internet do not last. Real products do. Chutes is becoming a real product. A subnet that generates actual revenue from actual users paying actual money for actual AI inference. That is what $43 million in Q1 network revenue looks like at the individual subnet level. And there is one more thing ChatGPT and Claude cannot offer that Chutes already has. Trusted Execution Environments. Your prompt gets encrypted on your device, shipped to a confidential compute GPU, and the lock only breaks inside the chip. The miner running the model physically cannot read your prompt. ChatGPT cannot promise that. Claude cannot promise that. Bittensor already built it. You are holding a network where the subnets are generating real revenue, shipping real privacy infrastructure, and replacing $20 a month centralised subscriptions with $10 a month decentralised inference. The people who use the product always understand the investment better than the people who only watch the price.
8:27

I pay Claude $20 a month. Most $TAO holders do too. There is a stack you can build in 15 minutes that fixes that completely. It runs on Bittensor. It costs $10. You do not write a single line of code. Here is how every AI chat product actually works under the hood. Three layers. Always three. The model. The brain. GPT, Claude, DeepSeek, Kimi, GLM. The inference layer. The GPU that runs the model when you hit send. The interface. The chat box you actually look at. ChatGPT and Claude bundle all three and hand you the result. You cannot change the model. You cannot change the inference. The interface is non-negotiable. Every prompt you type goes to a server run by a private company whose terms of service can quietly change next month. The anti-ChatGPT move is to pick each layer yourself. This is where $TAO comes in. Chutes is Subnet 64 on Bittensor. It is the inference layer. Open source models like DeepSeek, Kimi, GLM, and Llama get served by a global network of miner-operated GPUs. Validators score the output quality. The best inference wins the emissions. You hit send. A miner somewhere runs your prompt. You get the answer back. The TAO you hold is in part paying for the GPU you just used. The basic stack is one URL. chutes. ai/chat No account. No API key. No setup. Switch models mid-conversation. Web search built in. Image generation. File uploads. Free. The advanced stack is Chutes plus TypingMind. One-time license. No recurring fee. Plugins, agents, custom personas, a prompt library you build over months. Full model switching between Chutes, OpenAI, and Anthropic from the same window. Total cost: $10 a month to Chutes for inference. That $10 buys you $50 in actual usage. But here is the signal most people missed inside this story. Chutes ran a free tier until February. Then they killed it. Then they raised the minimum to $10 in May. Most people saw that as bad news. It is the opposite. Free things on the internet do not last. Real products do. Chutes is becoming a real product. A subnet that generates actual revenue from actual users paying actual money for actual AI inference. That is what $43 million in Q1 network revenue looks like at the individual subnet level. And there is one more thing ChatGPT and Claude cannot offer that Chutes already has. Trusted Execution Environments. Your prompt gets encrypted on your device, shipped to a confidential compute GPU, and the lock only breaks inside the chip. The miner running the model physically cannot read your prompt. ChatGPT cannot promise that. Claude cannot promise that. Bittensor already built it. You are holding a network where the subnets are generating real revenue, shipping real privacy infrastructure, and replacing $20 a month centralised subscriptions with $10 a month decentralised inference. The people who use the product always understand the investment better than the people who only watch the price.

2xnmore

26,871 просмотров • 29 дней назад

SOMEONE JUST BUILT AN ENTIRE COMPANY BRAIN INSIDE CLAUDE CODE IN 7 DAYS Not Obsidian. Not a doc... A living map of every department, every agent, every SOP on one screen. Click any node and the whole thing opens up: •⁠ ⁠who runs it •⁠ ⁠what SOPs are attached •⁠ ⁠what each person can touch that permission layer is the whole game an employee opens the chat and the AI already knows their access level. agents, data, SOPs surface in the conversation like you tagged them by hand. Obsidian cannot do this... no dev team. no six month build. no enterprise budget. just Claude Code and one week ClaudeKit is the only team you need to build something like this ( bonus: 20 best claude code workflows
1:20

SOMEONE JUST BUILT AN ENTIRE COMPANY BRAIN INSIDE CLAUDE CODE IN 7 DAYS Not Obsidian. Not a doc... A living map of every department, every agent, every SOP on one screen. Click any node and the whole thing opens up: •⁠ ⁠who runs it •⁠ ⁠what SOPs are attached •⁠ ⁠what each person can touch that permission layer is the whole game an employee opens the chat and the AI already knows their access level. agents, data, SOPs surface in the conversation like you tagged them by hand. Obsidian cannot do this... no dev team. no six month build. no enterprise budget. just Claude Code and one week ClaudeKit is the only team you need to build something like this ( bonus: 20 best claude code workflows

Hamza Khalid

63,055 просмотров • 6 дней назад

Introducing Kimi 2.6 Code. A Claude Code-like terminal experience built specifically for Kimi K2.6, effectively making it one of the most powerful open-source coding agents on the planet. Simply bring your API key and use /login. Repo here 👇
0:40

Introducing Kimi 2.6 Code. A Claude Code-like terminal experience built specifically for Kimi K2.6, effectively making it one of the most powerful open-source coding agents on the planet. Simply bring your API key and use /login. Repo here 👇

Pietro Schirano

135,641 просмотров • 2 месяцев назад

.signüll says his new company is building "Facebook News Feed 2.0": a highly personalized feed powered by 22 AI agents that lives on your home screen: "We basically ask you to install two widgets — a medium widget and a large widget that encapsulates the entire home screen. And those work together." "The medium widget...shows you precisely what you might need to know at this point in time. And the big widget, what we call a For You widget, which is just a feed." "We're building the new iteration of the Facebook News Feed that's entirely AI-generated about your life. Highly personal, and that lives directly on your home screen. You can browse it as easily [as the feed]...We have 22 agents that work to generate content continuously for that feed."
1:43

.signüll says his new company is building "Facebook News Feed 2.0": a highly personalized feed powered by 22 AI agents that lives on your home screen: "We basically ask you to install two widgets — a medium widget and a large widget that encapsulates the entire home screen. And those work together." "The medium widget...shows you precisely what you might need to know at this point in time. And the big widget, what we call a For You widget, which is just a feed." "We're building the new iteration of the Facebook News Feed that's entirely AI-generated about your life. Highly personal, and that lives directly on your home screen. You can browse it as easily [as the feed]...We have 22 agents that work to generate content continuously for that feed."

TBPN

59,006 просмотров • 2 месяцев назад

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.
0:37

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,871 просмотров • 24 дней назад

FOR THOSE WHO ARE CONFUSED… We experience TIME as a straight line, one moment after another, PAST TO PRESENT TO FUTURE. But that is only how it appears from inside the system. Beings in higher dimensions, what some call “ORACLES” OR “GODS,” do not experience time like this. They do not move through it. They observe it in its entirety. A closer analogy would be CHANNELS ON A SCREEN. What is playing on FOX and what is playing on CBS is not separate in existence, it is only separated by perspective. Both are happening at the same time, fully active, fully real. In the same way, what we call 1950 and what we call 2004 are not distant points moving away from each other. They are both present within the same total field of reality. From that level of awareness, nothing is being “waited on.” There is NO DELAY. There is only ACCESS. A shift of perception is all that is needed, like changing the channel. So if everything exists at once, then your FUTURE is not something that is coming toward you. It is something that already exists. The version of you 20 YEARS FROM NOW is already there. You have already CHOSEN THAT PATH, you have already GONE THROUGH WHAT COMES WITH IT, you have already LIVED THROUGH IT ALL. And what you are doing now is not creating it. You are MOVING THROUGH IT. Slowly remembering why you are there at all.
0:23

FOR THOSE WHO ARE CONFUSED… We experience TIME as a straight line, one moment after another, PAST TO PRESENT TO FUTURE. But that is only how it appears from inside the system. Beings in higher dimensions, what some call “ORACLES” OR “GODS,” do not experience time like this. They do not move through it. They observe it in its entirety. A closer analogy would be CHANNELS ON A SCREEN. What is playing on FOX and what is playing on CBS is not separate in existence, it is only separated by perspective. Both are happening at the same time, fully active, fully real. In the same way, what we call 1950 and what we call 2004 are not distant points moving away from each other. They are both present within the same total field of reality. From that level of awareness, nothing is being “waited on.” There is NO DELAY. There is only ACCESS. A shift of perception is all that is needed, like changing the channel. So if everything exists at once, then your FUTURE is not something that is coming toward you. It is something that already exists. The version of you 20 YEARS FROM NOW is already there. You have already CHOSEN THAT PATH, you have already GONE THROUGH WHAT COMES WITH IT, you have already LIVED THROUGH IT ALL. And what you are doing now is not creating it. You are MOVING THROUGH IT. Slowly remembering why you are there at all.

THE VOICE 🌹 🗣🎙🇺🇸🦅🌎⚓💜♠️CHRIST CONSCIOUSNESS

39,969 просмотров • 7 дней назад

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch
35:25

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

192,024 просмотров • 2 месяцев назад

A 23-person company now runs on 1 founder and a team of AI agents that never ask for a raise. He gave them names. Meet Nolan, head of content. 1 human types a task into a chatbot. Nolan reads it. He hands it to 1 of his 7 sub-agents to finish. That’s the whole team. Above Nolan sits a chief agent. The executives prompt the chief. He splits the job across every department head, then merges the answers into 1 reply. Employees skip the chief. They talk straight to their department head by chatbot, or by voice. You can call Nolan and he answers like a person. The onboarding doc shows 7 example use cases. A new hire is running the whole system in 1 afternoon. No salaries. No PTO. No 1:1s. No Slack drama. The entire company fits on 1 screen. This is what an org chart looks like when the staff never sleep.
1:14

A 23-person company now runs on 1 founder and a team of AI agents that never ask for a raise. He gave them names. Meet Nolan, head of content. 1 human types a task into a chatbot. Nolan reads it. He hands it to 1 of his 7 sub-agents to finish. That’s the whole team. Above Nolan sits a chief agent. The executives prompt the chief. He splits the job across every department head, then merges the answers into 1 reply. Employees skip the chief. They talk straight to their department head by chatbot, or by voice. You can call Nolan and he answers like a person. The onboarding doc shows 7 example use cases. A new hire is running the whole system in 1 afternoon. No salaries. No PTO. No 1:1s. No Slack drama. The entire company fits on 1 screen. This is what an org chart looks like when the staff never sleep.

Spike 1%

90,074 просмотров • 15 дней назад

An entire empire was overthrown over a two percent tax on a breakfast beverage. Look at what you tolerate now. You are taxed when you earn it. Taxed when you spend it. Taxed when you save it. Taxed when you invest it. And when you die, they tax whatever is left. That is not a system. That is a harvest. You commute in a car you paid sales tax to buy. You drive it on roads you were already taxed to build. You fill it with gas taxed by the gallon. When you sell that car, the next buyer pays sales tax on it again. The same car. Taxed every time it changes hands. You arrive at a job where your salary is cut before it ever touches your hands. If you work for yourself, you pay both sides. Two people on paper. Neither one keeps what they earned. Then you go home. Every bill you open has a government standing behind it with its hand out. You buy a house with money they already took their share of. Then they charge you property tax on it every year for the rest of your life. You want to renovate your own kitchen. You need a permit. You want to build a deck on your own land. You need a permit. You pay for the property. Then you pay for permission to use it. Stop paying property tax and they seize your home. Not because you missed a mortgage payment. Because you missed a payment to the government for the privilege of keeping what is already yours. You do not own your home. You rent it from the state. If you leave something behind for your children, they are taxed on what you were already taxed to earn. The same wealth. Taxed at every stage of your life. Then taxed one final time because you had the audacity to die. They found a way to monetize your absence. We are told this is the price of civilization. It is not. It is architecture. The most effective prison ever built is the one where the inmates believe they are free. They did not take your freedom. They priced you out of it. If you kept the full value of your labor, you would be free within years. Not decades. Years. The system cannot allow that. A machine built on consumption needs a consumer that never stops. You did not sign a social contract. You were assigned one. Now pay attention. They spent decades perfecting the extraction of your productivity. Now they are building the technology to replace you. AI is not coming for your job because corporations are greedy. It is coming because a system that already takes half your output just realized it can take all of it. Without needing you in the equation. You were never the point of this arrangement. You were the input. And the moment they engineer a cheaper one, you become a rounding error on a quarterly earnings call. They did not build AI to free you. They built it to finish what the tax code started. It was never about the tea. It was about the precedent. Today we hand over half our waking lives and thank them for the potholes. You do not live in a free economy. You live in a subscription you never signed up for. And the penalty for canceling is everything you have.
0:57

An entire empire was overthrown over a two percent tax on a breakfast beverage. Look at what you tolerate now. You are taxed when you earn it. Taxed when you spend it. Taxed when you save it. Taxed when you invest it. And when you die, they tax whatever is left. That is not a system. That is a harvest. You commute in a car you paid sales tax to buy. You drive it on roads you were already taxed to build. You fill it with gas taxed by the gallon. When you sell that car, the next buyer pays sales tax on it again. The same car. Taxed every time it changes hands. You arrive at a job where your salary is cut before it ever touches your hands. If you work for yourself, you pay both sides. Two people on paper. Neither one keeps what they earned. Then you go home. Every bill you open has a government standing behind it with its hand out. You buy a house with money they already took their share of. Then they charge you property tax on it every year for the rest of your life. You want to renovate your own kitchen. You need a permit. You want to build a deck on your own land. You need a permit. You pay for the property. Then you pay for permission to use it. Stop paying property tax and they seize your home. Not because you missed a mortgage payment. Because you missed a payment to the government for the privilege of keeping what is already yours. You do not own your home. You rent it from the state. If you leave something behind for your children, they are taxed on what you were already taxed to earn. The same wealth. Taxed at every stage of your life. Then taxed one final time because you had the audacity to die. They found a way to monetize your absence. We are told this is the price of civilization. It is not. It is architecture. The most effective prison ever built is the one where the inmates believe they are free. They did not take your freedom. They priced you out of it. If you kept the full value of your labor, you would be free within years. Not decades. Years. The system cannot allow that. A machine built on consumption needs a consumer that never stops. You did not sign a social contract. You were assigned one. Now pay attention. They spent decades perfecting the extraction of your productivity. Now they are building the technology to replace you. AI is not coming for your job because corporations are greedy. It is coming because a system that already takes half your output just realized it can take all of it. Without needing you in the equation. You were never the point of this arrangement. You were the input. And the moment they engineer a cheaper one, you become a rounding error on a quarterly earnings call. They did not build AI to free you. They built it to finish what the tax code started. It was never about the tea. It was about the precedent. Today we hand over half our waking lives and thank them for the potholes. You do not live in a free economy. You live in a subscription you never signed up for. And the penalty for canceling is everything you have.

Dustin

27,628 просмотров • 2 месяцев назад

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)
0:40

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,319 просмотров • 27 дней назад