Mr. Buzzoni's banner

Mr. Buzzoni

@polydao • 20,515 subscribers

Crafting the future of intelligence | AI Wizard & Builder | co-founder @polynternet | Partnerships & collabs welcome • DMs always open

Shorts

Atlassian's CEO after firing the engineer who built their $1.79B infrastructure and the guy released a 38-minute breakdown of everything he built, free for anyone to copy

Atlassian's CEO after firing the engineer who built their $1.79B infrastructure and the guy released a 38-minute breakdown of everything he built, free for anyone to copy

17,537,298 Aufrufe

THIS DOCUMENT FROM ANTHROPIC WILL LITERALLY GET YOU PROMOTED > the fastest way to reach a senior position is to automate your current job this technical paper shows how to encode your daily workflows into Claude build custom "Skills" to force the AI to do the heavy lifting: > package your routines into automated folders > the agent executes your tasks flawlessly in the background > it connects directly to your local tools via MCP servers hand off the junior work to the agent and easily claim your promotion grab the exact blueprint right here 👇

THIS DOCUMENT FROM ANTHROPIC WILL LITERALLY GET YOU PROMOTED > the fastest way to reach a senior position is to automate your current job this technical paper shows how to encode your daily workflows into Claude build custom "Skills" to force the AI to do the heavy lifting: > package your routines into automated folders > the agent executes your tasks flawlessly in the background > it connects directly to your local tools via MCP servers hand off the junior work to the agent and easily claim your promotion grab the exact blueprint right here 👇

366,340 Aufrufe

> do you understand what just happened to the job market > one person + 67 Claude Skills > does the work of an entire dev team > $20/month vs $200K/year in salaries > the Google engineer who automated 80% of his job? > this is the exact skill list he used > bookmark this. seriously. right now. 👇

> do you understand what just happened to the job market > one person + 67 Claude Skills > does the work of an entire dev team > $20/month vs $200K/year in salaries > the Google engineer who automated 80% of his job? > this is the exact skill list he used > bookmark this. seriously. right now. 👇

1,014,386 Aufrufe

I ABANDONED LOVABLE AFTER SEEING WHAT CLAUDE CODE CAN ACTUALLY DO basic generators are great for quick ideas but trying to build a premium site with Lovable feels like playing in a sandbox I gave Claude Code a few custom design skills instead 4 minutes later it built a premium design they would have quoted me $7,500 for the difference between generic templates and a skilled local agent is literally worth thousands grab the full guide below 👇

I ABANDONED LOVABLE AFTER SEEING WHAT CLAUDE CODE CAN ACTUALLY DO basic generators are great for quick ideas but trying to build a premium site with Lovable feels like playing in a sandbox I gave Claude Code a few custom design skills instead 4 minutes later it built a premium design they would have quoted me $7,500 for the difference between generic templates and a skilled local agent is literally worth thousands grab the full guide below 👇

176,242 Aufrufe

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE FABLE 5 + OBSIDIAN Andrej Karpathy (openai co-founder) shared an architecture that turns Claude into a persistent second brain instead of a basic chat window how it works: > you point Claude Code at an Obsidian vault folder > you drop articles, PDFs, or video transcripts into raw folders > Claude reads the files, updates topic summaries, and cross-references everything > the knowledge base compounds like interest instead of resetting on every new chat the setup is simple: > install and create a local vault directory > open the directory in Claude Code and paste Karpathy's wiki prompt: > > let the agent generate raw, wiki, and CLAUDE.md schema directories > drop any text file into raw and tell the model to ingest it > ask questions across the whole vault and query compiled summaries this eliminates rag database overhead and keeps your local vault organized how do you manage your local knowledge base?

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE FABLE 5 + OBSIDIAN Andrej Karpathy (openai co-founder) shared an architecture that turns Claude into a persistent second brain instead of a basic chat window how it works: > you point Claude Code at an Obsidian vault folder > you drop articles, PDFs, or video transcripts into raw folders > Claude reads the files, updates topic summaries, and cross-references everything > the knowledge base compounds like interest instead of resetting on every new chat the setup is simple: > install and create a local vault directory > open the directory in Claude Code and paste Karpathy's wiki prompt: > > let the agent generate raw, wiki, and CLAUDE.md schema directories > drop any text file into raw and tell the model to ingest it > ask questions across the whole vault and query compiled summaries this eliminates rag database overhead and keeps your local vault organized how do you manage your local knowledge base?

88,685 Aufrufe

One of the Epstein files now circulating is titled “MASSEUSES” It contains 254 entries, and every single line is fully redacted No names, no details - just page after page of blacked-out rows

One of the Epstein files now circulating is titled “MASSEUSES” It contains 254 entries, and every single line is fully redacted No names, no details - just page after page of blacked-out rows

967,542 Aufrufe

This is how you compress 100 hours of content into 10 minutes! just tried NotebookLM + Obsidian and it's actually insane > the "YouTube to NotebookLM" extension lets you dump entire channels into NotebookLM and get a structured mega-summary in minutes > Audio Overviews turns any PDF, report or notes into a podcast-style dialogue - perfect for walking or driving > Book Filter: upload your Obsidian vault + a new book, ask "is there anything new for me here?" - if no, skip it and save dozens of hours this combo feels like compression for knowledge the stack: 📁 NotebookLM ↳ 📁 YouTube to NotebookLM Chrome Extension ↳ this combo + Obsidian vault = unfair advantage

This is how you compress 100 hours of content into 10 minutes! just tried NotebookLM + Obsidian and it's actually insane > the "YouTube to NotebookLM" extension lets you dump entire channels into NotebookLM and get a structured mega-summary in minutes > Audio Overviews turns any PDF, report or notes into a podcast-style dialogue - perfect for walking or driving > Book Filter: upload your Obsidian vault + a new book, ask "is there anything new for me here?" - if no, skip it and save dozens of hours this combo feels like compression for knowledge the stack: 📁 NotebookLM ↳ 📁 YouTube to NotebookLM Chrome Extension ↳ this combo + Obsidian vault = unfair advantage

111,955 Aufrufe

THIS IS HOW YOU COMPRESS 100 HOURS INTO 10 MINUTES > just tried NotebookLM + Obsidian combo and honestly… this is insane > i didn’t expect NotebookLM to be this powerful the craziest part? > the "YouTube to NotebookLM" extension you can literally pull entire channels, dump all videos into NotebookLM and get a structured mega-summary in minutes > but two features completely blew my mind: Audio Overviews: > turns any PDF, report or notes into a podcast-style dialogue between two hosts > perfect for listening while walking or driving Book Filter: > upload your Obsidian knowledge base + a new book ask: "Is there anything new for me here?" if the answer is "no" skip it and save dozens of hours > this feels like compression for knowledge if you’re serious about learning fast, here’s the stack: 📁 NotebookLM ↳ 📁 YouTube to NotebookLM Chrome Extension ↳ 📁 Google Gemini ↳ this combo + Obsidian vault = unfair advantage

THIS IS HOW YOU COMPRESS 100 HOURS INTO 10 MINUTES > just tried NotebookLM + Obsidian combo and honestly… this is insane > i didn’t expect NotebookLM to be this powerful the craziest part? > the "YouTube to NotebookLM" extension you can literally pull entire channels, dump all videos into NotebookLM and get a structured mega-summary in minutes > but two features completely blew my mind: Audio Overviews: > turns any PDF, report or notes into a podcast-style dialogue between two hosts > perfect for listening while walking or driving Book Filter: > upload your Obsidian knowledge base + a new book ask: "Is there anything new for me here?" if the answer is "no" skip it and save dozens of hours > this feels like compression for knowledge if you’re serious about learning fast, here’s the stack: 📁 NotebookLM ↳ 📁 YouTube to NotebookLM Chrome Extension ↳ 📁 Google Gemini ↳ this combo + Obsidian vault = unfair advantage

215,522 Aufrufe

🚨 JUST IN: THE US GOVERNMENT JUST SHUT DOWN CLAUDE FABLE 5 FOR THE ENTIRE WORLD > a national security export control directive. effective immediately > every foreign national on earth - including Anthropic's own engineers who built the model - is now locked out > Fable 5 launched 4 days ago > it's already being classified like a weapons system > Anthropic says it's a misunderstanding > the order doesn't care > Opus 4.8 still runs. Fable 5 and Mythos 5 are gone until further notice AI just got its first export control. it won't be the last

🚨 JUST IN: THE US GOVERNMENT JUST SHUT DOWN CLAUDE FABLE 5 FOR THE ENTIRE WORLD > a national security export control directive. effective immediately > every foreign national on earth - including Anthropic's own engineers who built the model - is now locked out > Fable 5 launched 4 days ago > it's already being classified like a weapons system > Anthropic says it's a misunderstanding > the order doesn't care > Opus 4.8 still runs. Fable 5 and Mythos 5 are gone until further notice AI just got its first export control. it won't be the last

51,235 Aufrufe

THIS GUY HAD 1,283 NOTES AND HIS SYSTEM WAS DUMBER THAN A FOLDER that galaxy in the background is his Obsidian vault > looks incredible > does nothing dead notes, zero connections, zero value extracted from any of it > the fix isn't taking better notes > it's building a pipeline where Claude Opus 4.8 does the research, NotebookLM does the analysis, and every session feeds your vault automatically one command: > Claude Code searches YouTube for 10 relevant sources > passes them to NotebookLM - Google's servers do the heavy processing, not your tokens > NotebookLM runs full analysis, generates infographics, mindmaps, flashcards > everything lands as structured markdown in your Obsidian vault, linked and ready total time: 6 minutes > after a month the vault knows your thinking style. after a year it's a trained research assistant the $300K AI architects aren't taking better notes > they're building systems that compound 30-minute setup. full step-by-step in the article below 👇

THIS GUY HAD 1,283 NOTES AND HIS SYSTEM WAS DUMBER THAN A FOLDER that galaxy in the background is his Obsidian vault > looks incredible > does nothing dead notes, zero connections, zero value extracted from any of it > the fix isn't taking better notes > it's building a pipeline where Claude Opus 4.8 does the research, NotebookLM does the analysis, and every session feeds your vault automatically one command: > Claude Code searches YouTube for 10 relevant sources > passes them to NotebookLM - Google's servers do the heavy processing, not your tokens > NotebookLM runs full analysis, generates infographics, mindmaps, flashcards > everything lands as structured markdown in your Obsidian vault, linked and ready total time: 6 minutes > after a month the vault knows your thinking style. after a year it's a trained research assistant the $300K AI architects aren't taking better notes > they're building systems that compound 30-minute setup. full step-by-step in the article below 👇

48,417 Aufrufe

+$2,912 ON WEATHER MARKETS WITHOUT PREDICTING A SINGLE TEMPERATURE 80.6% win rate. 1,200+ positions. fully automated the pattern is simple and works on any weather market: > every specific temperature range has a low hit probability > market often overprices narrow exact bands at $0.05-$0.10 > the No side sits at $0.90-$1.00 -> almost free money > buy No across 20+ cities simultaneously > 87.7% resolve in your favor by pure base-rate math > run it with a bot 24/7 so you never miss a market you don't need a weather model -> you need to understand that exact values almost never land > full profile: real edge survives stress. this one did

57,916 Aufrufe

> my university experience: $200 textbook. $600 Adobe. $300 Office. > students now: one .edu email → $10,000+ in tools I am still paying for all of it. monthly. this is not fair

> my university experience: $200 textbook. $600 Adobe. $300 Office. > students now: one .edu email → $10,000+ in tools I am still paying for all of it. monthly. this is not fair

58,040 Aufrufe

How a Misread Rule Turned $38 Into $20k on Polymarket most traders assumed the word already counted and rushed in > one guy just read the market rules carefully and waited $38 -> $20k came from understanding which event actually mattered, not from guessing what Trump would say profile:

59,925 Aufrufe

IF YOU TRADE WEATHER ON POLYMARKET - INSTALL THIS EXTENSION IMMEDIATELY > no new tabs. no switching between tools. just open the market and it's there this is what Poly Helper shows you on any weather market: > ECMWF + GFS + ICON models aggregated > model confidence score > temperature range > 7-day forecast they're also adding: sports intel, macro, MrBeast views, Pentagon pizza index and the meta-play: > top 1000 on the points leaderboard get up to 50% of any potential Polymarket airdrop > early users stack points from day one invite code: K68UMR 👇

IF YOU TRADE WEATHER ON POLYMARKET - INSTALL THIS EXTENSION IMMEDIATELY > no new tabs. no switching between tools. just open the market and it's there this is what Poly Helper shows you on any weather market: > ECMWF + GFS + ICON models aggregated > model confidence score > temperature range > 7-day forecast they're also adding: sports intel, macro, MrBeast views, Pentagon pizza index and the meta-play: > top 1000 on the points leaderboard get up to 50% of any potential Polymarket airdrop > early users stack points from day one invite code: K68UMR 👇

34,717 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Atlassian's revenue: $1.79 billion last quarter Atlassian's move: fire the engineer who built their infrastructure his move: post a 38-minute breakdown of every system he built, free for anyone to copy what he revealed: > Envoy proxy instead of enterprise load balancers > sidecar architecture for auth, logging, rate limits > DynamoDB + SQS for async provisioning > Packer + SaltStack for automated VM deployments at scale Atlassian charges per employee across 350,000 customers this guy just handed you the enterprise playbook for free save this

Atlassian's revenue: $1.79 billion last quarter Atlassian's move: fire the engineer who built their infrastructure his move: post a 38-minute breakdown of every system he built, free for anyone to copy what he revealed: > Envoy proxy instead of enterprise load balancers > sidecar architecture for auth, logging, rate limits > DynamoDB + SQS for async provisioning > Packer + SaltStack for automated VM deployments at scale Atlassian charges per employee across 350,000 customers this guy just handed you the enterprise playbook for free save this

21,714,959 Aufrufe • vor 2 Monaten

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

81,407 Aufrufe • vor 5 Tagen

KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT Karpathy said we're in the 1960s of AI - most people using Claude Opus 4.8 are still acting like it's just a search engine > software 3.0 - LLMs as operating systems, not chatbots > autonomous agents that run entire workflows without you watching the 32 skills in this article are how you actually cross that line bookmark this 👇

KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT Karpathy said we're in the 1960s of AI - most people using Claude Opus 4.8 are still acting like it's just a search engine > software 3.0 - LLMs as operating systems, not chatbots > autonomous agents that run entire workflows without you watching the 32 skills in this article are how you actually cross that line bookmark this 👇

565,870 Aufrufe • vor 1 Monat

This girl from IBM explained how Claude works better than most AI engineers could in 8 minutes > search used to match words, not meaning > then AI learned to understand intent > then RAG gave LLMs external memory - so they could read your documents > then agents arrived - now the AI decides what to search, when, and why the hardest part of AI isn't generating the answer it's knowing what to look at first full video above

This girl from IBM explained how Claude works better than most AI engineers could in 8 minutes > search used to match words, not meaning > then AI learned to understand intent > then RAG gave LLMs external memory - so they could read your documents > then agents arrived - now the AI decides what to search, when, and why the hardest part of AI isn't generating the answer it's knowing what to look at first full video above

524,161 Aufrufe • vor 2 Monaten

KARPATHY JUST DROPPED 2 HOURS OF BRUTAL HONESTY ABOUT AI > we're nowhere near real autonomous agents - including Claude Opus 4.8 > AGI will blend into daily life and nobody will notice > he quit AI research to fix education. that's the problem he thinks matters more save this👇

KARPATHY JUST DROPPED 2 HOURS OF BRUTAL HONESTY ABOUT AI > we're nowhere near real autonomous agents - including Claude Opus 4.8 > AGI will blend into daily life and nobody will notice > he quit AI research to fix education. that's the problem he thinks matters more save this👇

328,829 Aufrufe • vor 1 Monat

Vasilios Syrakis is back after the massive success of his Atlassian video, he just dropped a follow-up addressing everything the stuff people really wanted to know: > no university degree, dropped out after 10th grade, started in help desk > taught himself everything from scratch - books, videos, no mentor > he didn't break any NDA - Atlassian published more detailed info themselves > the architecture was 10 years old - he'd build it completely differently today and the thing that hit hardest: > to everyone who felt impostor syndrome watching his first video - he said the gap between you and someone who knows more is usually just time, not intelligence the full response is above and he's building a control plane from scratch on camera soon so you can see exactly how it's done

Vasilios Syrakis is back after the massive success of his Atlassian video, he just dropped a follow-up addressing everything the stuff people really wanted to know: > no university degree, dropped out after 10th grade, started in help desk > taught himself everything from scratch - books, videos, no mentor > he didn't break any NDA - Atlassian published more detailed info themselves > the architecture was 10 years old - he'd build it completely differently today and the thing that hit hardest: > to everyone who felt impostor syndrome watching his first video - he said the gap between you and someone who knows more is usually just time, not intelligence the full response is above and he's building a control plane from scratch on camera soon so you can see exactly how it's done

392,279 Aufrufe • vor 2 Monaten

> do you understand what Claude Opus 4.8 just did to the Google job market > a senior Google engineer with 11 years of experience > stacked 32 Claude skills on top of his workflow > 8hrs → 2-3hrs per day > $95K developer vs $300K AI architect > same job. different stack. very different salary > the exact skill list is here 👇

> do you understand what Claude Opus 4.8 just did to the Google job market > a senior Google engineer with 11 years of experience > stacked 32 Claude skills on top of his workflow > 8hrs → 2-3hrs per day > $95K developer vs $300K AI architect > same job. different stack. very different salary > the exact skill list is here 👇

286,905 Aufrufe • vor 1 Monat

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free

192,952 Aufrufe • vor 1 Monat

ANDREJ KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT we're in the 1960s of LLMs most people using Claude have the wrong mental model Software 3.0. LLMs as operating systems how to actually think about and work with them save this 👇

ANDREJ KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT we're in the 1960s of LLMs most people using Claude have the wrong mental model Software 3.0. LLMs as operating systems how to actually think about and work with them save this 👇

326,008 Aufrufe • vor 2 Monaten

Jane Street needed a 4,032 GPU liquid-cooled data center just to run their trading models > that tells you everything about how much money this firm makes and why their quants start at $400K/year someone just got inside and filmed it > custom AI and trading agents trained specifically for this firm - off-the-shelf doesn't cut it > packets processed in under 100 nanoseconds > copper over fiber because electrons beat light at that scale > automated kill switches to shut algorithms down before downtime costs millions > financial privacy of their positions is protected at infrastructure level - nothing leaks 20 years ago their cluster was 6 Dell boxes on an office floor > this is the machine now what do you think - is this level of infrastructure even possible for smaller firms?

Jane Street needed a 4,032 GPU liquid-cooled data center just to run their trading models > that tells you everything about how much money this firm makes and why their quants start at $400K/year someone just got inside and filmed it > custom AI and trading agents trained specifically for this firm - off-the-shelf doesn't cut it > packets processed in under 100 nanoseconds > copper over fiber because electrons beat light at that scale > automated kill switches to shut algorithms down before downtime costs millions > financial privacy of their positions is protected at infrastructure level - nothing leaks 20 years ago their cluster was 6 Dell boxes on an office floor > this is the machine now what do you think - is this level of infrastructure even possible for smaller firms?

241,402 Aufrufe • vor 2 Monaten

the skill gap between $95K and $300K right now is Claude Opus agent architecture this 2-hour guide closes that gap companies are paying $150K-300K/year for engineers who know this most of them have no idea this guide exists watch it. build it. charge for it

the skill gap between $95K and $300K right now is Claude Opus agent architecture this 2-hour guide closes that gap companies are paying $150K-300K/year for engineers who know this most of them have no idea this guide exists watch it. build it. charge for it

232,244 Aufrufe • vor 2 Monaten

This guy plugged a DGX Spark (the $3K Nvidia box) and a Mac Mini M4 together to run AI and what happened next surprised everyone > the Nvidia box handles the hard part - processing your prompt in milliseconds > Mac Mini M4 handles the fast part - generating the response at memory bandwidth speeds nothing else can match > together they hit 84 tokens per second on Llama - 6x faster than the Spark alone > running compute agents locally on this setup means your data never leaves your hardware > two boxes. two different architectures. one AI system that Deepseek runs at data center scale he ran it on his desk save this. the way we build local AI is about to change

This guy plugged a DGX Spark (the $3K Nvidia box) and a Mac Mini M4 together to run AI and what happened next surprised everyone > the Nvidia box handles the hard part - processing your prompt in milliseconds > Mac Mini M4 handles the fast part - generating the response at memory bandwidth speeds nothing else can match > together they hit 84 tokens per second on Llama - 6x faster than the Spark alone > running compute agents locally on this setup means your data never leaves your hardware > two boxes. two different architectures. one AI system that Deepseek runs at data center scale he ran it on his desk save this. the way we build local AI is about to change

153,432 Aufrufe • vor 1 Monat

KARPATHY JUST DROPPED A 2-HOUR INTERVIEW AND IT'S THE MOST HONEST THING IN AI RIGHT NOW watched the whole thing. three things hit me hard: > we're nowhere near real agents - including Claude > AGI will blend into daily life and nobody will notice > he quit AI research to fix education. because that's the actual problem save this 👇

KARPATHY JUST DROPPED A 2-HOUR INTERVIEW AND IT'S THE MOST HONEST THING IN AI RIGHT NOW watched the whole thing. three things hit me hard: > we're nowhere near real agents - including Claude > AGI will blend into daily life and nobody will notice > he quit AI research to fix education. because that's the actual problem save this 👇

195,787 Aufrufe • vor 2 Monaten

Claude Code will grill you with 40+ questions before writing a single line of code > it's called /grill-me - 3 sentences long. most impactful skill I use instead of jumping straight to code - it walks every branch of your design tree until there's zero ambiguity > every question reveals something you hadn't thought of other skills I use daily: > /write-a-prd - idea → proper product doc > /prd-to-issues - doc → GitHub issues automatically > /tdd - tests first, forces edge case thinking before code > /improve-codebase-architecture -> full structural review of your codebase all links and full breakdown in my article full video from Matt Pocock 👇

Claude Code will grill you with 40+ questions before writing a single line of code > it's called /grill-me - 3 sentences long. most impactful skill I use instead of jumping straight to code - it walks every branch of your design tree until there's zero ambiguity > every question reveals something you hadn't thought of other skills I use daily: > /write-a-prd - idea → proper product doc > /prd-to-issues - doc → GitHub issues automatically > /tdd - tests first, forces edge case thinking before code > /improve-codebase-architecture -> full structural review of your codebase all links and full breakdown in my article full video from Matt Pocock 👇

223,964 Aufrufe • vor 3 Monaten

THE 1-HOUR OBSIDIAN LECTURE THAT CHANGES HOW YOU THINK ABOUT YOUR VAULT > Nick Milo breaks down Obsidian Bases > the feature that finally makes Obsidian a real database, not just a folder of markdown files > save this. watch it before you set up your vault👇

THE 1-HOUR OBSIDIAN LECTURE THAT CHANGES HOW YOU THINK ABOUT YOUR VAULT > Nick Milo breaks down Obsidian Bases > the feature that finally makes Obsidian a real database, not just a folder of markdown files > save this. watch it before you set up your vault👇

190,563 Aufrufe • vor 3 Monaten

This 1-hour Stanford lecture covers more about the tech inside Claude than most $1,000 AI bootcamps it answers the exact questions they'll ask you in an AI product or engineering interview: > why can Claude see images but only reply with text? > why does making the model "smarter" at reading make it better at generating output? > what is the "MoT" architecture that lets Claude learn vision without losing logic? > why is physical world interaction still the hardest problem to solve? the person who understands this framework doesn't just use Claude - they explain how it's built save this before your next interview

This 1-hour Stanford lecture covers more about the tech inside Claude than most $1,000 AI bootcamps it answers the exact questions they'll ask you in an AI product or engineering interview: > why can Claude see images but only reply with text? > why does making the model "smarter" at reading make it better at generating output? > what is the "MoT" architecture that lets Claude learn vision without losing logic? > why is physical world interaction still the hardest problem to solve? the person who understands this framework doesn't just use Claude - they explain how it's built save this before your next interview

77,740 Aufrufe • vor 1 Monat

THIS 11-PAGE CLAUDE LOOP ENGINEERING PLAYBOOK IS THE CHEAT CODE FOR SENIOR DEV PROMOTIONS typing prompts line by line won't get you hired. you need to know how to design self-prompting loops: > Discovery: agent finds its own work from logs, failing tests, and commits > Handoff: tasks execute in isolated git worktrees to prevent parallel collisions > Verification: a second reviewer agent audits the builder's code to catch blind spots > Persistence and Scheduling: code writes to disk and loops run 24/7 on a timer the shift is simple: stop prompting the agent, build the system that prompts it read the full setup blueprint 👇

THIS 11-PAGE CLAUDE LOOP ENGINEERING PLAYBOOK IS THE CHEAT CODE FOR SENIOR DEV PROMOTIONS typing prompts line by line won't get you hired. you need to know how to design self-prompting loops: > Discovery: agent finds its own work from logs, failing tests, and commits > Handoff: tasks execute in isolated git worktrees to prevent parallel collisions > Verification: a second reviewer agent audits the builder's code to catch blind spots > Persistence and Scheduling: code writes to disk and loops run 24/7 on a timer the shift is simple: stop prompting the agent, build the system that prompts it read the full setup blueprint 👇

44,111 Aufrufe • vor 24 Tagen

Obsidian + Claude = 24/7 personal operating system Greg Isenberg just showed how to bridge a local Markdown vault and Claude Code via Obsidian CLI the setup that solves the context bottleneck: > /context - loads the complete model of your projects, schedule, and interests so you never have to re-explain details > /today - compiles calendar slots, tasks, and notes from the last week into a prioritized daily plan > /challenge - scans past entries to find contradictions, testing your current beliefs against your own history > /graduate - a custom command that Claude Code wrote for itself to extract structured essays from daily logs the people who build this tonight will never work the same way again bookmark this before your next setup session 👇

Obsidian + Claude = 24/7 personal operating system Greg Isenberg just showed how to bridge a local Markdown vault and Claude Code via Obsidian CLI the setup that solves the context bottleneck: > /context - loads the complete model of your projects, schedule, and interests so you never have to re-explain details > /today - compiles calendar slots, tasks, and notes from the last week into a prioritized daily plan > /challenge - scans past entries to find contradictions, testing your current beliefs against your own history > /graduate - a custom command that Claude Code wrote for itself to extract structured essays from daily logs the people who build this tonight will never work the same way again bookmark this before your next setup session 👇

51,346 Aufrufe • vor 29 Tagen

CLAUDE + OBSIDIAN = THE ONLY AI FORMAT THAT WILL SURVIVE THE NEXT DECADE I struggled to build a functional second brain until I applied Karpathy's system -> I used to rely on walled gardens to store my thoughts, jumping from one app to the next then I moved everything to plain text in Obsidian and connected it to Claude seeing the AI read my entire folder locally completely upgraded my approach to work: > you point the AI directly at your local directory for instant context > you own your data forever because everything stays on your machine > the setup eliminates subscription fees and messy database exports > the open format is immune to startup failures because simple text lasts forever complex note apps will eventually shut down. a plain text folder works for a lifetime watch the breakdown 👇

CLAUDE + OBSIDIAN = THE ONLY AI FORMAT THAT WILL SURVIVE THE NEXT DECADE I struggled to build a functional second brain until I applied Karpathy's system -> I used to rely on walled gardens to store my thoughts, jumping from one app to the next then I moved everything to plain text in Obsidian and connected it to Claude seeing the AI read my entire folder locally completely upgraded my approach to work: > you point the AI directly at your local directory for instant context > you own your data forever because everything stays on your machine > the setup eliminates subscription fees and messy database exports > the open format is immune to startup failures because simple text lasts forever complex note apps will eventually shut down. a plain text folder works for a lifetime watch the breakdown 👇

38,279 Aufrufe • vor 24 Tagen

1 HOUR WITH KARPATHY. SAVE THIS BEFORE YOU OPEN CLAUDE CODE TODAY > autonomous agents that improve themselves without a human in the loop that's where Claude Opus 4.8 is heading > the 32 skills in this article are the foundation Karpathy explains what's coming

1 HOUR WITH KARPATHY. SAVE THIS BEFORE YOU OPEN CLAUDE CODE TODAY > autonomous agents that improve themselves without a human in the loop that's where Claude Opus 4.8 is heading > the 32 skills in this article are the foundation Karpathy explains what's coming

69,151 Aufrufe • vor 1 Monat