Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

This has been possible for months and barely anyone is doing it Months ago, Andrej Karpathy, a co-founder of OpenAI, open-sourced a project that gets you the best possible answers instead of trusting one model on its own. It's called LLM Council. Repo: /karpathy/llm-council The idea in two lines:...

undefinedKi's profile picture

Yarchi

13,362 subscribers

21,488 görüntüleme • 3 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Andrej Karpathy spent a weekend building something the world wasn't ready for. The idea: don't trust one model. Make them debate each other. He called it LLM Council. GPT, Claude, Gemini, Grok, same prompt. Every model critiquing each other. A "Chairman" AI synthesizing truth from their disagreements. He called it a "vibe coded hack." It went viral within the hour. Because everyone already knew he was right. MIT proved it, accuracy jumps from 70% to 95% when models debate instead of answer alone. The problem? It runs locally. You need Python. A terminal. Most people can't or won't set it up. So they went back to doing it manually: → Ask ChatGPT. Get an answer. → Paste into Claude. Different answer. → Paste into Gemini. Another. → Compare. Lose your train of thought. Give up. I discovered Cuey, which is literally Karpathy's insight (LLM Council) made accessible for EVERYONE! 👍 It's a Chrome extension 👍 You write just one prompt 👍 30+ models debate in the background 👍 No terminal. No setup. No copy-pasting. We need more solutions like this that allows more people to get the most from AI without coding. Give it a try →
1:57

Andrej Karpathy spent a weekend building something the world wasn't ready for. The idea: don't trust one model. Make them debate each other. He called it LLM Council. GPT, Claude, Gemini, Grok, same prompt. Every model critiquing each other. A "Chairman" AI synthesizing truth from their disagreements. He called it a "vibe coded hack." It went viral within the hour. Because everyone already knew he was right. MIT proved it, accuracy jumps from 70% to 95% when models debate instead of answer alone. The problem? It runs locally. You need Python. A terminal. Most people can't or won't set it up. So they went back to doing it manually: → Ask ChatGPT. Get an answer. → Paste into Claude. Different answer. → Paste into Gemini. Another. → Compare. Lose your train of thought. Give up. I discovered Cuey, which is literally Karpathy's insight (LLM Council) made accessible for EVERYONE! 👍 It's a Chrome extension 👍 You write just one prompt 👍 30+ models debate in the background 👍 No terminal. No setup. No copy-pasting. We need more solutions like this that allows more people to get the most from AI without coding. Give it a try →

Priyanka Vergadia

12,246 görüntüleme • 5 ay önce

is genspark ($50M ARR in 6mo) underrated next to chatgpt, claude, gemini, and manus? i spent 34 minutes testing its “super ai agent” and how it actually works. 1/ you write one prompt and it runs through gpt-5, claude sonnet, gemini 2.5, and mistral large then gives you the best response. 2/ you upload one image and it runs it through nano banana, flux, and bytedance then returns the most realistic version. 3/ you generate a video and genspark routes it through wan 2.2, pika labs, gen-2, and runway ml combining the best clips and motion. 4/ you paste an idea for slides and it uses gpt-5, claude 3 opus, gemini advanced, and genspark’s slide model to create a full deck with visuals and market data. 5/ AI slides and building a fundraising deck with a few prompts (wasn't perfect, but it was a good start for my personal workflow) what's cool about genspark is it's inexpensive and does it all. kinda like the costco of LLMs. TLDR; you hand it one prompt + input, and genspark routes sub-tasks across models and tools behind the scenes. it’s orchestration over one ideal model. perspective shift. instead of jumping from model to model, llm to llm, genspark shows what the next generation of ai will look like orchestration over obsession. and for the rest of us using it, the only thing that matters is getting the best outcome. what other AI app should I review next? i'll keep doing it if it's helpful for folks.
34:35

is genspark ($50M ARR in 6mo) underrated next to chatgpt, claude, gemini, and manus? i spent 34 minutes testing its “super ai agent” and how it actually works. 1/ you write one prompt and it runs through gpt-5, claude sonnet, gemini 2.5, and mistral large then gives you the best response. 2/ you upload one image and it runs it through nano banana, flux, and bytedance then returns the most realistic version. 3/ you generate a video and genspark routes it through wan 2.2, pika labs, gen-2, and runway ml combining the best clips and motion. 4/ you paste an idea for slides and it uses gpt-5, claude 3 opus, gemini advanced, and genspark’s slide model to create a full deck with visuals and market data. 5/ AI slides and building a fundraising deck with a few prompts (wasn't perfect, but it was a good start for my personal workflow) what's cool about genspark is it's inexpensive and does it all. kinda like the costco of LLMs. TLDR; you hand it one prompt + input, and genspark routes sub-tasks across models and tools behind the scenes. it’s orchestration over one ideal model. perspective shift. instead of jumping from model to model, llm to llm, genspark shows what the next generation of ai will look like orchestration over obsession. and for the rest of us using it, the only thing that matters is getting the best outcome. what other AI app should I review next? i'll keep doing it if it's helpful for folks.

GREG ISENBERG

62,242 görüntüleme • 11 ay önce

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.
0:35

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

elvis

39,593 görüntüleme • 7 ay önce

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.
0:38

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.

elvis

79,836 görüntüleme • 9 ay önce

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this
13:23

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,559 görüntüleme • 4 ay önce

Andrej Karpathy quietly shipped the best second brain idea in years not an app. a pattern. let an llm maintain a wiki of your notes. you dump sources, it reads them, links them, files them. knowledge compounds like interest. someone built it into a free claude code plugin. setup is two commands: claude plugin marketplace add AgriciDaniel/claude-obsidian claude plugin install claude-obsidian@agricidaniel-claude-obsidian then open obsidian, open claude code in the same folder, type /wiki. that's it. your notes are now queryable by claude and they get richer every time you read something. bookmark this. best thing you'll build this weekend.
0:42

Andrej Karpathy quietly shipped the best second brain idea in years not an app. a pattern. let an llm maintain a wiki of your notes. you dump sources, it reads them, links them, files them. knowledge compounds like interest. someone built it into a free claude code plugin. setup is two commands: claude plugin marketplace add AgriciDaniel/claude-obsidian claude plugin install claude-obsidian@agricidaniel-claude-obsidian then open obsidian, open claude code in the same folder, type /wiki. that's it. your notes are now queryable by claude and they get richer every time you read something. bookmark this. best thing you'll build this weekend.

Avid

339,134 görüntüleme • 3 ay önce

1M free tokens every month for Opus 5.5, GPT-5.6, Grok 4.6, DeepSeek V4 and 29 more models with zero card 😳 I tested every model this account can access. all 33 answered through one OpenAI-compatible API what you get for free: - 1M tokens every month - 60 requests per minute - Claude, GPT, Grok, Gemini, DeepSeek, Qwen, Kimi and GLM models - works with Cursor, Cline, opencode, Claude Code, Continue and Aider setup: 1. go to 2. create your free account 3. generate your own API key 4. set the base URL to 5. pick a model and test one call CodeCraft is a third-party gateway, so use it for testing and keep private work off it bookmark this before the model list changes
0:39

1M free tokens every month for Opus 5.5, GPT-5.6, Grok 4.6, DeepSeek V4 and 29 more models with zero card 😳 I tested every model this account can access. all 33 answered through one OpenAI-compatible API what you get for free: - 1M tokens every month - 60 requests per minute - Claude, GPT, Grok, Gemini, DeepSeek, Qwen, Kimi and GLM models - works with Cursor, Cline, opencode, Claude Code, Continue and Aider setup: 1. go to 2. create your free account 3. generate your own API key 4. set the base URL to 5. pick a model and test one call CodeCraft is a third-party gateway, so use it for testing and keep private work off it bookmark this before the model list changes

Israfil

14,690 görüntüleme • 15 gün önce

Can your agent finally edit your videos? Yup, it's a repo called video use, by Browser Use. You put the raw footage in a folder. Then Claude Code or Codex edits it. It removes the filler words, cuts the dead space, adds the subtitles, and renders the file. Then it checks its own cut points. Most creators use the same small set of edits in every video. That style stays in your head and in your hands. This repo puts it in a file that an agent can read. People ask for a full YouTube channel on day one. They see bad results, and they stop. Start with one format instead. - One founder loom into a 60 second launch video - 3 clips out of one podcast recording Then make the format a system. Then you operate the system, or you sell it. - Real estate agents need listing videos - Coaches need clips - Agencies need ad variations Manual installation with git clone is possible. For 95% of people, the agent is faster. Here's how i intalled it: - Gave the setup prompt to Claude Code with shell access - Let it read install.md - Installed the repo - Connected FFmpeg - Registered the skill
4:22

Can your agent finally edit your videos? Yup, it's a repo called video use, by Browser Use. You put the raw footage in a folder. Then Claude Code or Codex edits it. It removes the filler words, cuts the dead space, adds the subtitles, and renders the file. Then it checks its own cut points. Most creators use the same small set of edits in every video. That style stays in your head and in your hands. This repo puts it in a file that an agent can read. People ask for a full YouTube channel on day one. They see bad results, and they stop. Start with one format instead. - One founder loom into a 60 second launch video - 3 clips out of one podcast recording Then make the format a system. Then you operate the system, or you sell it. - Real estate agents need listing videos - Coaches need clips - Agencies need ad variations Manual installation with git clone is possible. For 95% of people, the agent is faster. Here's how i intalled it: - Gave the setup prompt to Claude Code with shell access - Let it read install.md - Installed the repo - Connected FFmpeg - Registered the skill

The Startup Ideas Podcast (SIP) 🧃

15,605 görüntüleme • 1 ay önce

single most useful thing for my local ai setup that made life easy is my 2x DGX Spark becoming one serving box for every device i own here is how i do it: > 1. the two sparks run one vLLM server together with one endpoint, i use dgx sparks, you can use any nodes that can run an llm > 2. install tailscale to have all your nodes and machines on the same tailnet, the endpoint lives there so every device reaches it from anywhere and no port is open to the internet > 3. that one tailnet endpoint with the exposed port is your base url for everything, it speaks OpenAI chat, OpenAI Responses and Anthropic Messages, so any chat app, coding agent or phone bot you point at it talks to the same model > 4. the server also answers to the name "local", so clients can ask for "local" instead of a model name and when i swap the model on the servers nothing on the devices needs a config change. right now it's serving GLM 5.3-Flash, next week it can be something else this video below is the whole thing running end to end, orange dots are requests going in, white and green are tokens coming back it takes however many requests you throw at it, your config decides how many run at once and the rest wait their turn, when several run together each request's tok/s drops a bit while the box moves more tokens in total. mine is set to one at a time right now, so when every device fires together they queue up this setup really improved my quality of life with local ai, if you get stuck anywhere setting it up leave a comment and i'll help you
1:04

single most useful thing for my local ai setup that made life easy is my 2x DGX Spark becoming one serving box for every device i own here is how i do it: > 1. the two sparks run one vLLM server together with one endpoint, i use dgx sparks, you can use any nodes that can run an llm > 2. install tailscale to have all your nodes and machines on the same tailnet, the endpoint lives there so every device reaches it from anywhere and no port is open to the internet > 3. that one tailnet endpoint with the exposed port is your base url for everything, it speaks OpenAI chat, OpenAI Responses and Anthropic Messages, so any chat app, coding agent or phone bot you point at it talks to the same model > 4. the server also answers to the name "local", so clients can ask for "local" instead of a model name and when i swap the model on the servers nothing on the devices needs a config change. right now it's serving GLM 5.3-Flash, next week it can be something else this video below is the whole thing running end to end, orange dots are requests going in, white and green are tokens coming back it takes however many requests you throw at it, your config decides how many run at once and the rest wait their turn, when several run together each request's tok/s drops a bit while the box moves more tokens in total. mine is set to one at a time right now, so when every device fires together they queue up this setup really improved my quality of life with local ai, if you get stuck anywhere setting it up leave a comment and i'll help you

Sudo su

32,379 görüntüleme • 9 gün önce

iit's wild that this still isn't the default way people use AI. Andrew Ng, a co-founder of Google Brain, gave a talk that crossed 2 million views: stop feeding your AI a folder of notes, build it a graph it can actually think with. his point is simple, stop making your AI read the whole vault to answer one thing. give it a graph, a router that points, an index that scores, edges that link, and it walks straight to the answer. it compounds, cheaper and faster the more you add. here's the whole thing: > point Claude at your notes and have it write a tiny router, your CLAUDE.md > build an index, one line per note, so it always knows where an answer lives > keep each note to one idea, and link the ones that depend on each other > make retrieval run as code, so it scores and opens the right files before the model thinks > tell it to prove the graph beats a flat folder on speed and cost, then keep the index fresh on every write set it up once and your AI stops guessing. it already knows your world before you type a word. full 12-step guide below. bookmark this.
0:23

iit's wild that this still isn't the default way people use AI. Andrew Ng, a co-founder of Google Brain, gave a talk that crossed 2 million views: stop feeding your AI a folder of notes, build it a graph it can actually think with. his point is simple, stop making your AI read the whole vault to answer one thing. give it a graph, a router that points, an index that scores, edges that link, and it walks straight to the answer. it compounds, cheaper and faster the more you add. here's the whole thing: > point Claude at your notes and have it write a tiny router, your CLAUDE.md > build an index, one line per note, so it always knows where an answer lives > keep each note to one idea, and link the ones that depend on each other > make retrieval run as code, so it scores and opens the right files before the model thinks > tell it to prove the graph beats a flat folder on speed and cost, then keep the index fresh on every write set it up once and your AI stops guessing. it already knows your world before you type a word. full 12-step guide below. bookmark this.

KingWilliam

15,099 görüntüleme • 2 ay önce

an engineer openai laid off in january open-sourced the exact thing that made gpt-6 astra worth $200 a month, three weeks after they walked him out. call it revenge, call it the most expensive severance package in history. sam altman spent two years telling everyone the magic was locked in the cloud. one bitter ex-employee proved it fits in a github repo, and now the $200 seat is guarding a moat that is already public. here is what he leaked, and it runs local for about $6 instead of $400: -> pull his open repo, load it onto one nvidia card, and you have the part of gpt-6 astra people were actually paying for -> point cursor, cline and every app at localhost, and none of them notice they left openai for a model that never phones home -> route the rare heavy job to a rented gpu by the hour and keep the daily work local for the cost of power -> your $200 chatgpt seat and your $200 claude seat both go dark the same week the repo trended here is the part they will fight me on: openai and anthropic were never selling the model, they were selling the fact that it lived somewhere you could not reach. one guy they underpaid moved it somewhere you can. the $200 was the distance, and he deleted the distance. drop your $400 stack to a $6 local model and run the thing they fired him for sharing. the full build is in the article below, save it before they get the repo taken down.
0:29

an engineer openai laid off in january open-sourced the exact thing that made gpt-6 astra worth $200 a month, three weeks after they walked him out. call it revenge, call it the most expensive severance package in history. sam altman spent two years telling everyone the magic was locked in the cloud. one bitter ex-employee proved it fits in a github repo, and now the $200 seat is guarding a moat that is already public. here is what he leaked, and it runs local for about $6 instead of $400: -> pull his open repo, load it onto one nvidia card, and you have the part of gpt-6 astra people were actually paying for -> point cursor, cline and every app at localhost, and none of them notice they left openai for a model that never phones home -> route the rare heavy job to a rented gpu by the hour and keep the daily work local for the cost of power -> your $200 chatgpt seat and your $200 claude seat both go dark the same week the repo trended here is the part they will fight me on: openai and anthropic were never selling the model, they were selling the fact that it lived somewhere you could not reach. one guy they underpaid moved it somewhere you can. the $200 was the distance, and he deleted the distance. drop your $400 stack to a $6 local model and run the thing they fired him for sharing. the full build is in the article below, save it before they get the repo taken down.

starmex

12,339 görüntüleme • 29 gün önce

CLAUDE + OBSIDIAN + KARPATHY'S LLM WIKI = A WIKI THAT MAINTAINS ITSELF run this once and your research compounds instead of evaporating sources go in, a wiki comes out, and a loop keeps it honest • three layers, one owner each > the schema - CLAUDE.md, you and the agent co-evolve it > the wiki - markdown the agent owns. it writes, you read > raw sources - immutable, read only, never edited • three operations on repeat > ingest - read the source, write the summary, log one line > query - answer with citations, file it back as a new page > lint - contradictions, orphans and dead links caught early RAG re-derives the same answer from raw chunks on every query. you pay for that thinking again, every time you ask this wiki gets written once and stays current. 10-15 pages per source, nearly 100 sources on the index alone month one it saves you an hour a day. month six it knows your field better than the person you're up against for the senior seat "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase" - Andrej Karpathy the stack: 📁 Obsidian ↳ 📁 Claude ↳ 📁 Karpathy LLM-Wiki ↳
0:30

CLAUDE + OBSIDIAN + KARPATHY'S LLM WIKI = A WIKI THAT MAINTAINS ITSELF run this once and your research compounds instead of evaporating sources go in, a wiki comes out, and a loop keeps it honest • three layers, one owner each > the schema - CLAUDE.md, you and the agent co-evolve it > the wiki - markdown the agent owns. it writes, you read > raw sources - immutable, read only, never edited • three operations on repeat > ingest - read the source, write the summary, log one line > query - answer with citations, file it back as a new page > lint - contradictions, orphans and dead links caught early RAG re-derives the same answer from raw chunks on every query. you pay for that thinking again, every time you ask this wiki gets written once and stays current. 10-15 pages per source, nearly 100 sources on the index alone month one it saves you an hour a day. month six it knows your field better than the person you're up against for the senior seat "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase" - Andrej Karpathy the stack: 📁 Obsidian ↳ 📁 Claude ↳ 📁 Karpathy LLM-Wiki ↳

Annatar.md

16,939 görüntüleme • 17 gün önce

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch
49:16

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch

GREG ISENBERG

156,806 görüntüleme • 3 ay önce

Your Plan SUCKS! 👀 Inspired by the legend Andrej Karpathy himself, I created a new skill: LLM Council. Create better plans, by committee. Supports: > Codex CLI > Gemini CLI > Claude Code > OpenCode Call the skill with your feature that you'd like to build. It will ask you some clarifying question, and then launch up to four parallel planning agents to create a detailed plan. Once the plans are in, all plans are anonymized and the "The Judge" will critique and choose the best plan *OR* the best parts from all of them. Finally, it will output a final-plan, which you can review and refine. I even created a nice UI for you to review and refine your plans. This Skill has been tested on Linux only, but should work on other platforms. Please report any bugs! Links in the comments.
0:28

Your Plan SUCKS! 👀 Inspired by the legend Andrej Karpathy himself, I created a new skill: LLM Council. Create better plans, by committee. Supports: > Codex CLI > Gemini CLI > Claude Code > OpenCode Call the skill with your feature that you'd like to build. It will ask you some clarifying question, and then launch up to four parallel planning agents to create a detailed plan. Once the plans are in, all plans are anonymized and the "The Judge" will critique and choose the best plan *OR* the best parts from all of them. Finally, it will output a final-plan, which you can review and refine. I even created a nice UI for you to review and refine your plans. This Skill has been tested on Linux only, but should work on other platforms. Please report any bugs! Links in the comments.

am.will

69,134 görüntüleme • 8 ay önce

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers
0:51

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

James Rochabrun

61,608 görüntüleme • 3 ay önce

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.
0:21

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Charlie Hills

38,355 görüntüleme • 1 ay önce

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below
0:20

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

kai

32,740 görüntüleme • 2 ay önce

ANTHROPIC OPEN-SOURCED A FREE REPO THAT TURNS CLAUDE INTO A SALES REP, A MARKETER AND A FINANCE LEAD. PEOPLE ARE ALREADY SELLING THIS AS A SERVICE You're not prompting from scratch. You're hiring a department How to set it up: 1. Open Cowork. In the Claude desktop app, open Cowork and go to Customize. You'll see a Browse Plugins button. That's the marketplace 2. Pick your first role. Inside you'll find sales, marketing, finance, legal, data, customer support, product management and more. Each plugin has the skills for that role already baked in, plus the connectors it would use. Install the one you need most 3. Put it to work standalone. It works day one with no setup. Trigger a workflow with a slash command like /sales:call-prep or /data:write-query, paste your notes, and it already knows what good output looks like 4. Connect its tools to supercharge it. Authorize the tools that role uses, your CRM, your analytics, your data warehouse. Standalone is the intern. Connected is the senior hire 5. Build the rest of the team. Install more roles and they work together in one session. Data pulls the numbers, finance reconciles them, marketing turns it into a report. One operator, a full cross-functional team, no payroll This is the same base layer Claude for Legal and Claude for Financial Services are built on. You're getting it for free Full breakdown in my article below. Bookmark this
0:30

ANTHROPIC OPEN-SOURCED A FREE REPO THAT TURNS CLAUDE INTO A SALES REP, A MARKETER AND A FINANCE LEAD. PEOPLE ARE ALREADY SELLING THIS AS A SERVICE You're not prompting from scratch. You're hiring a department How to set it up: 1. Open Cowork. In the Claude desktop app, open Cowork and go to Customize. You'll see a Browse Plugins button. That's the marketplace 2. Pick your first role. Inside you'll find sales, marketing, finance, legal, data, customer support, product management and more. Each plugin has the skills for that role already baked in, plus the connectors it would use. Install the one you need most 3. Put it to work standalone. It works day one with no setup. Trigger a workflow with a slash command like /sales:call-prep or /data:write-query, paste your notes, and it already knows what good output looks like 4. Connect its tools to supercharge it. Authorize the tools that role uses, your CRM, your analytics, your data warehouse. Standalone is the intern. Connected is the senior hire 5. Build the rest of the team. Install more roles and they work together in one session. Data pulls the numbers, finance reconciles them, marketing turns it into a report. One operator, a full cross-functional team, no payroll This is the same base layer Claude for Legal and Claude for Financial Services are built on. You're getting it for free Full breakdown in my article below. Bookmark this

Yarchi

31,798 görüntüleme • 4 ay önce

"It's basically what we call the Blackstone model, which is, you don't take over the whole company right, you buy the largest stake in it and you use that to control it. And so that's the model starting with the US, but basically every country in the world is being subject to this. And so they have planted through these small focus groups of private intelligence, and it's a combination of private intelligence, private equity, and IT firms, and they're basically coming together as one. And they set up their teams in each country to basically take it over strategically. There's a playbook for this..." Emanuel Pastreich of 🥷 🔗
8:37

"It's basically what we call the Blackstone model, which is, you don't take over the whole company right, you buy the largest stake in it and you use that to control it. And so that's the model starting with the US, but basically every country in the world is being subject to this. And so they have planted through these small focus groups of private intelligence, and it's a combination of private intelligence, private equity, and IT firms, and they're basically coming together as one. And they set up their teams in each country to basically take it over strategically. There's a playbook for this..." Emanuel Pastreich of 🥷 🔗

Geopolitics & Empire

18,051 görüntüleme • 7 ay önce