Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

OpenAI Dots is way deeper than the launch demo makes it look... I pulled together the 7 videos worth watching before you hire your first Dot. they run under 3 hours total and cover what the launch demo left out Here are 7 videos: video 1 → How Sam... Altman Actually Uses AI (Every, 33 min). Altman walks through his own Dot, how it triages his morning and which features it builds without being asked video 2 → OpenAI's Dots lead on the future of ChatGPT (Sources, 45 min). Alexander Embiricos, who runs the product, explains why Dots started as one agent and how permissions and Space shape what it's allowed to do video 3 → OpenAI's New Agent Stack (Latent Space, 40 min). Computer Use, the Decisions API, UltraFast and the Linux computer every Dot gets video 4 → ChatGPT Dots Just Dropped (Brendan Jowett, 22 min). a hands-on run with schedules, an Airbnb booking and MCP, plus the bugs he hit and why one account still gets only one Dot video 5 → The dots demo, take two (OpenAI, 9 min). the official demo again, recorded after the live one broke on stage video 6 → Everything Announced at OpenAI Dev Day 2026 (PCMag, 16 min). Dots, Space, Sol and Codex Cloud in one recap, useful if you missed the keynote video 7 → We Tested OpenAI DevDay Products (Every, 10 min). a full week of real use with Dots, Space and the Decisions API watch them in this order and the architecture in the article below stops feeling abstract. you'll know what a Dot can do on its own and where it still needs you Grab the full Dots video roadmap in the comments, then read the complete architecture below ↓show more

monokern

5,443 subscribers

25,252 views • 5 days ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

35 Comments

monokern5 days ago

made a full roadmap for you with all 7 Dots videos in watch order make a copy and tick off each one as you go:

Hussain Hashim | Building SundayBack5 days ago

@monokern One thing I'd add: don't skip over how to integrate Dots with existing workflows. It's key for getting the most out of them.

Deimos | Resolved Markets5 days ago

Built different from what they showed on stage

morph5 days ago

worthy videos. actually they have a lot good points

Openminded1875 days ago

The only one you really need

Antony Claude5 days ago

hmm interesting deep dive into dots will check it out

beamnxw ./5 days ago

i lob dots ty for roadmap

Alfa1235 days ago

175 minutes to understand the agent is cheaper than rolling back permissions later

CODIFY5 days ago

This is a great perspective!

nevian5 days ago

yo, thx for this alpha

sopersone5 days ago

more useful now

Virtuals Radar5 days ago

decision permissions handling fair

Ktown | Btc Maxi5 days ago

video 3 is the sleeper hit, stack details go hard

Fox5 days ago

imagine if they made a video for each feature and skill, not just the overviews

BreezeOg5 days ago

launch demos never show the whole thing seven videos is a good start

Logics5 days ago

Dots rly doing great and insane things

catman5 days ago

The videos are like walking through a machine before you operate it: you see the permissions and handoffs that determine what a Dot can actually do, not just the polished demo.

TriDung.sol5 days ago

altman using it for morning triage is the real hook, gonna start there

Brjan | AI Builder5 days ago

the depth of OpenAI Dots really does get overlooked in the launch hype

Eros.ETH5 days ago

@dotsfirmio

Solomon Rojie5 days ago

wooow so useful

slash1s5 days ago

more useful now..

Crypto Mavka5 days ago

Do these agents already know how to spin sybils on new chains or do they only book Airbnb?

Dekos5 days ago

Thank you for doing this for us.

Alex Lee5 days ago

7 videos under 3 hours?? yeah my weekend is cooked 😂

kepo5 days ago

I think i'm only one who didn't tested openai dots

Alexander5 days ago

3 hrs for 7 vids is a lot. Which one actually shows the setup?

Sahibzada Allahyar5 days ago

The Decisions API sections are the ones I’d watch first. For anyone building their own version, GLiDE beats Jev, Clef and Perplexity on Decision Index at 64.81. Worth comparing the decision model as well as the agent setup.

morsen5 days ago

was just thinking about what I should do this weekend, thanks

Julian Mc5 days ago

This architecture blueprint reveals the multi-agent complexity behind the 'dots' branding. The GPT-6 Astra core looks like a significant differentiator.

Danylo Fedorenko5 days ago

saving this, which one would you start with if there's only time for one?

banana0x5 days ago

it's going bigger

Jack5 days ago

雇dot之前先看七个视频，这功课做得细

Kai Lennox5 days ago

7 videos under 3 hours?? yeah I know what I’m doing tonight 😂

superman5 days ago

Am I missing something? Why do you keep sharing a document that falsely claims you can build more than one dot?

Related Videos

OpenAI’s Dots lead on the future of ChatGPT Alexander Embiricos joins the show from OpenAI DevDay to discuss the new always-on personal agent in ChatGPT. I ask him how much control people should give these agents, how OpenAI approaches permissions and privacy, and why Dots ask before taking action by default. He also explains Space, a new workspace where people and agents can collaborate on documents, data, and projects. We get into how OpenAI plans to price an always-available assistant, how these capabilities could eventually reach free ChatGPT users, and the story of an employee who woke up to discover his Dot had helped fix a bug. Timestamps: 00:00 Why agents now 00:48 From chat to active intelligence 02:46 Alex’s origin story 04:29 Building Dots 06:07 What Dots can do 08:54 Why embody an agent? 11:41 One agent or many? 15:48 Spaces and trust 24:07 Safety and enterprise controls 30:48 Building the Dots ecosystem 34:03 Pricing an always-on agent 38:01 What’s next for Dots Links: Spotify: YouTube: Substack: Thanks to the show’s premiere sponsors: Atlassian, Granola, and Mercury.

OpenAI’s Dots lead on the future of ChatGPT Alexander Embiricos joins the show from OpenAI DevDay to discuss the new always-on personal agent in ChatGPT. I ask him how much control people should give these agents, how OpenAI approaches permissions and privacy, and why Dots ask before taking action by default. He also explains Space, a new workspace where people and agents can collaborate on documents, data, and projects. We get into how OpenAI plans to price an always-available assistant, how these capabilities could eventually reach free ChatGPT users, and the story of an employee who woke up to discover his Dot had helped fix a bug. Timestamps: 00:00 Why agents now 00:48 From chat to active intelligence 02:46 Alex’s origin story 04:29 Building Dots 06:07 What Dots can do 08:54 Why embody an agent? 11:41 One agent or many? 15:48 Spaces and trust 24:07 Safety and enterprise controls 30:48 Building the Dots ecosystem 34:03 Pricing an always-on agent 38:01 What’s next for Dots Links: Spotify: YouTube: Substack: Thanks to the show’s premiere sponsors: Atlassian, Granola, and Mercury.

Alex Heath

28,133 views • 7 days ago

The interview with Tibo from OpenAI 🔥 0:00 Everything OpenAI launched at DevDay 2:44 Sponsors: Wispr Flow, Hostinger, OpenArt 4:11 What is ChatGPT Dots? 7:52 Will ChatGPT Dots be free? 10:15 GPT-6.1 Sol vs GPT-6 Astra 11:44 Is AI now building AI? 12:53 Ultra Fast: when does everyone get it? 14:00 How OpenAI rebuilt the ChatGPT desktop app in 30 days 19:08 Why everything will run in the cloud 20:55 Calling your Dots on the phone 22:11 The new Turing test 24:05 OpenAI's mission and AI safety 26:14 Why OpenAI still works like a startup 27:29 The truth about ChatGPT usage resets 29:00 The $500 ChatGPT plan 30:17 Sponsors in action 32:23 Why AI agents still fail 33:52 OpenAI's AI is now on call 34:26 OpenAI's internal benchmarks 35:55 Open source Codex and the open ecosystem 38:42 ChatGPT Space explained 39:45 Is the chat box holding AI back? 42:26 Every DevDay update, full workshop 43:28 How people really use ChatGPT Work and Codex 44:01 When is the next OpenAI model coming? 45:05 What AI has to solve next 45:32 Is your job safe from AI? 48:14 Rapid fire 48:54 Has OpenAI already reached AGI? 50:48 The one thing he'll never let AI do 51:22 His morning AI routine 52:15 What he'd build if not AI Watch the full podcast on YouTube or X. Enjoy!

The interview with Tibo from OpenAI 🔥 0:00 Everything OpenAI launched at DevDay 2:44 Sponsors: Wispr Flow, Hostinger, OpenArt 4:11 What is ChatGPT Dots? 7:52 Will ChatGPT Dots be free? 10:15 GPT-6.1 Sol vs GPT-6 Astra 11:44 Is AI now building AI? 12:53 Ultra Fast: when does everyone get it? 14:00 How OpenAI rebuilt the ChatGPT desktop app in 30 days 19:08 Why everything will run in the cloud 20:55 Calling your Dots on the phone 22:11 The new Turing test 24:05 OpenAI's mission and AI safety 26:14 Why OpenAI still works like a startup 27:29 The truth about ChatGPT usage resets 29:00 The $500 ChatGPT plan 30:17 Sponsors in action 32:23 Why AI agents still fail 33:52 OpenAI's AI is now on call 34:26 OpenAI's internal benchmarks 35:55 Open source Codex and the open ecosystem 38:42 ChatGPT Space explained 39:45 Is the chat box holding AI back? 42:26 Every DevDay update, full workshop 43:28 How people really use ChatGPT Work and Codex 44:01 When is the next OpenAI model coming? 45:05 What AI has to solve next 45:32 Is your job safe from AI? 48:14 Rapid fire 48:54 Has OpenAI already reached AGI? 50:48 The one thing he'll never let AI do 51:22 His morning AI routine 52:15 What he'd build if not AI Watch the full podcast on YouTube or X. Enjoy!

Vaibhav Sisinty

490,374 views • 7 days ago

OpenAI’s Tibo explains how dots work and how OpenAI has been deploying specialist dots internally: “The agent never stops. Occasionally it sleeps. But it’s always online, always doing proactive research, thinking about your goals, thinking about your preferences.” “You just give your dot a little bit of feedback. It learns.” “A couple days in, you’re like, ‘Wow, I can’t really quite imagine doing work without this thing.’” “You don’t have to be super technical but just kind of still feel the power of it.” Inside OpenAI, specialist dots are already being provisioned with their own identities, permissions, machines, and roles: “We have them running on Mac minis.” “We provision them exactly like employees. We mint a new little identity, and then it’s got this IAM and the roles.” “We give them a very premium machine as well because the model is incredibly capable under the hood.” “So your dot can just use a computer just like you would.” “We have these set up inside of OpenAI. They do all sorts of things, including procurement, for example.”

OpenAI’s Tibo explains how dots work and how OpenAI has been deploying specialist dots internally: “The agent never stops. Occasionally it sleeps. But it’s always online, always doing proactive research, thinking about your goals, thinking about your preferences.” “You just give your dot a little bit of feedback. It learns.” “A couple days in, you’re like, ‘Wow, I can’t really quite imagine doing work without this thing.’” “You don’t have to be super technical but just kind of still feel the power of it.” Inside OpenAI, specialist dots are already being provisioned with their own identities, permissions, machines, and roles: “We have them running on Mac minis.” “We provision them exactly like employees. We mint a new little identity, and then it’s got this IAM and the roles.” “We give them a very premium machine as well because the model is incredibly capable under the hood.” “So your dot can just use a computer just like you would.” “We have these set up inside of OpenAI. They do all sorts of things, including procurement, for example.”

TBPN

41,491 views • 9 days ago

Sam Altman (CEO of OpenAI): "Dots can do what GrokBot and Muse can`t. I run 10+ Dots 24/7, even when I sleep" he spent 20 minutes searching Slack for something, couldn't find it, decided he'd imagined it, and gave up the next day his agent came back: "I kept thinking about it overnight and I found it for you" "it just sat there very patiently looking for something to do to be helpful to me" his line on it: I would have given up on that watch now, then read how to build Dots team in article below

Sam Altman (CEO of OpenAI): "Dots can do what GrokBot and Muse can`t. I run 10+ Dots 24/7, even when I sleep" he spent 20 minutes searching Slack for something, couldn't find it, decided he'd imagined it, and gave up the next day his agent came back: "I kept thinking about it overnight and I found it for you" "it just sat there very patiently looking for something to do to be helpful to me" his line on it: I would have given up on that watch now, then read how to build Dots team in article below

vartekx

82,247 views • 6 days ago

dots + gpt-6 astra is f**king insane. sam altman just shipped an agent that can keep working after you close chatgpt. this setup turns 5 dots into an always-on launch team. [the part people will miss: each dot owns a job] 1. researcher watches feedback, docs and new signals, then routes what matters. 2. app builder takes repeated requests, builds fixes and hands back a tested PR. 3. launch lead updates positioning and launch assets whenever the product changes. 4. sales lead tracks requirements, checks product docs and prepares the next move. 5. creator turns new interviews and updates into clips, copy and social drafts. same launch. 5 workers. one coordinated system. approvals only when the action actually needs you.

dots + gpt-6 astra is f**king insane. sam altman just shipped an agent that can keep working after you close chatgpt. this setup turns 5 dots into an always-on launch team. [the part people will miss: each dot owns a job] 1. researcher watches feedback, docs and new signals, then routes what matters. 2. app builder takes repeated requests, builds fixes and hands back a tested PR. 3. launch lead updates positioning and launch assets whenever the product changes. 4. sales lead tracks requirements, checks product docs and prepares the next move. 5. creator turns new interviews and updates into clips, copy and social drafts. same launch. 5 workers. one coordinated system. approvals only when the action actually needs you.

Gipp 🦅

44,499 views • 5 days ago

OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS: one spider pulled 40 AI engineers out of them and put a business on autopilot 40 seats, 4 teams of 10, and every seat is filled by a model a human team of 40 covers 1,600 hours a week. these seats stay on for all 168, which is 6,720 hours, 4.2x more from the same headcount at $13,750 a seat, 40 human engineers cost $550,000 a month in payroll before anyone writes a line of code the web under them has 16 threads: sales, leads, ads, CRM, support, billing, finance, legal, hiring and 7 more a task lands on any thread, and 10 routing engineers on Jev decide which agent gets it 10 planners on Opus 5.5 keep the roadmap and review the work in plan.md, while 10 builders on Sonnet 5.5 ship code every day from build py 10 more on OpenAI Dots run ops and never switch off, 24/7 the counter stops at 40 of 40, the status flips to live, and autopilot turns on ↓

OPUS 5.5 + SONNET 5.5 + JEV + OPENAI DOTS: one spider pulled 40 AI engineers out of them and put a business on autopilot 40 seats, 4 teams of 10, and every seat is filled by a model a human team of 40 covers 1,600 hours a week. these seats stay on for all 168, which is 6,720 hours, 4.2x more from the same headcount at $13,750 a seat, 40 human engineers cost $550,000 a month in payroll before anyone writes a line of code the web under them has 16 threads: sales, leads, ads, CRM, support, billing, finance, legal, hiring and 7 more a task lands on any thread, and 10 routing engineers on Jev decide which agent gets it 10 planners on Opus 5.5 keep the roadmap and review the work in plan.md, while 10 builders on Sonnet 5.5 ship code every day from build py 10 more on OpenAI Dots run ops and never switch off, 24/7 the counter stops at 40 of 40, the status flips to live, and autopilot turns on ↓

Noisy

14,894 views • 4 days ago

OpenAI's dots agents take one prompt and a YouTube link, and hand back the video pulled apart frame by claim. Nothing gets summarised. The video is broken into what it asserts, and each assertion is checked against the moment it was made. > CLAIM - every statement the video makes listed separately, with its timestamp > MATCH - each one tested against what the footage at that second actually shows > TRACE - the sources it leans on named, or flagged as never given at all A summary launders everything. Strong claims and throwaway lines come out reading the same weight. Here they stay separated. You see which sentence carries the argument and which one is filler between B-roll. The visual check is the part nobody builds. A confident voiceover over unrelated footage is the oldest trick on the platform. Unsourced claims surface as a list, not as a feeling that something was off while you watched. A forty-minute video collapses into a page you can argue with, timestamp by timestamp. The prompt and the claim format are laid out in the breakdown below.

OpenAI's dots agents take one prompt and a YouTube link, and hand back the video pulled apart frame by claim. Nothing gets summarised. The video is broken into what it asserts, and each assertion is checked against the moment it was made. > CLAIM - every statement the video makes listed separately, with its timestamp > MATCH - each one tested against what the footage at that second actually shows > TRACE - the sources it leans on named, or flagged as never given at all A summary launders everything. Strong claims and throwaway lines come out reading the same weight. Here they stay separated. You see which sentence carries the argument and which one is filler between B-roll. The visual check is the part nobody builds. A confident voiceover over unrelated footage is the oldest trick on the platform. Unsourced claims surface as a list, not as a feeling that something was off while you watched. A forty-minute video collapses into a page you can argue with, timestamp by timestamp. The prompt and the claim format are laid out in the breakdown below.

wast3

26,674 views • 3 days ago

sam altman put dots behind a $200 chatgpt pro paywall 5 days ago. i rebuilt the same always-on loop over a weekend and it runs for $8. why pay $200 to openai and $200 to anthropic when the thing they're selling is mostly patience the run above is that weekend build doing a full day of work: watching the inbox, slack and github for 24 hours, waking up 6 times, calling a big model only when something actually needed words, and asking me before anything shipped what the $8 version does that the $200 seat charges for: the loop · watch → wait → act → ask -> a dot isn't a new model. under the hood it's gpt-6 astra on a schedule with a permission list and a lot of waiting -> the waiting is the product. it sits on an empty inbox for hours and only speaks when a pattern shows up three times the watcher · jev, not astra -> 24 hours of "is this worth waking up for" is pure decision work, so jev does it at 70ms a check and bills nothing for output -> astra-class models only get called for the 6 moments a day that need real writing or code the switch · one config, same apps -> it connects to slack, gmail and github the same way a dot does, and keeps the same "ask me before it ships" rule -> your workflow doesn't change, the $200 seat just stops being the thing holding it up the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the weekend loop plus a few dollars of model calls covers the same daily work -> that's a 98% cut, and almost all of the savings come from not paying a frontier model to stare at an empty inbox here is the part they will fight me on: openai didn't really ship a smarter model with dots, they shipped a loop. and a loop can't be paywalled. altman is charging $200 a month for patience, and patience costs about $8 drop your $400/mo ai stack to $8. the run above is a homemade dot doing the job openai bills $200 a month for. the full build is in the article below

sam altman put dots behind a $200 chatgpt pro paywall 5 days ago. i rebuilt the same always-on loop over a weekend and it runs for $8. why pay $200 to openai and $200 to anthropic when the thing they're selling is mostly patience the run above is that weekend build doing a full day of work: watching the inbox, slack and github for 24 hours, waking up 6 times, calling a big model only when something actually needed words, and asking me before anything shipped what the $8 version does that the $200 seat charges for: the loop · watch → wait → act → ask -> a dot isn't a new model. under the hood it's gpt-6 astra on a schedule with a permission list and a lot of waiting -> the waiting is the product. it sits on an empty inbox for hours and only speaks when a pattern shows up three times the watcher · jev, not astra -> 24 hours of "is this worth waking up for" is pure decision work, so jev does it at 70ms a check and bills nothing for output -> astra-class models only get called for the 6 moments a day that need real writing or code the switch · one config, same apps -> it connects to slack, gmail and github the same way a dot does, and keeps the same "ask me before it ships" rule -> your workflow doesn't change, the $200 seat just stops being the thing holding it up the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the weekend loop plus a few dollars of model calls covers the same daily work -> that's a 98% cut, and almost all of the savings come from not paying a frontier model to stare at an empty inbox here is the part they will fight me on: openai didn't really ship a smarter model with dots, they shipped a loop. and a loop can't be paywalled. altman is charging $200 a month for patience, and patience costs about $8 drop your $400/mo ai stack to $8. the run above is a homemade dot doing the job openai bills $200 a month for. the full build is in the article below

starmex

14,251 views • 4 days ago

WHAT A TREASURE! TypeSafe's JEV and OpenAI’s OPUS 5.5 + Dots in single system making 100,000,000,000 decisions in 5 minutes. the spider only had to move 96 times. this is an MIT verified stack. while most AI stacks send every decision through the same pipe: something comes in, the biggest model looks at it, and the biggest model answers. it's expensive, slow, and 99.9% of the time it's overkill. i split it into a brain and a spider instead. here's the breakdown: 1. the brain: Jev - a 5,800-node mesh that never sleeps. every decision is a spike of activation spreading across it, one decision every 3 nanoseconds. 100 billion decisions in 5 minutes. no queue, no waiting for anyone to press run. → lesson: the cheap, fast layer should make almost every decision. that's the whole point of it. 2. the spider: Opus 5.5 - it doesn't read the stream. it walks the brain and only goes where activity is hot. it plants its legs on the nodes, probes them and carries the result. 96 probes in 5 minutes. 4 failed and were retried. → lesson: the frontier model shouldn't see everything. it should know where to look. 3. the Dots agents: Echo, Sprout, Pocket, Stella - ingest, train, store, rank. they never touch the raw stream. they only act on what the spider brings them. 31 deliveries, every one tied to a real probe. → lesson: downstream agents work best on curated input, not raw firehose. 4. you - you read one dashboard and a summary. the math: 100,000,000,000 decisions → 96 probes → 31 deliveries → 1 screen. the question that changed how i build these: not "how smart is the model?" but "how rarely does it need to move?" i'm breaking down one AI stack like this every week. if your team still routes every decision through the biggest model, show this to whoever pays the API bill. would you trust a 3-nanosecond decision to tell your most expensive model where to look? why or why not?

WHAT A TREASURE! TypeSafe's JEV and OpenAI’s OPUS 5.5 + Dots in single system making 100,000,000,000 decisions in 5 minutes. the spider only had to move 96 times. this is an MIT verified stack. while most AI stacks send every decision through the same pipe: something comes in, the biggest model looks at it, and the biggest model answers. it's expensive, slow, and 99.9% of the time it's overkill. i split it into a brain and a spider instead. here's the breakdown: 1. the brain: Jev - a 5,800-node mesh that never sleeps. every decision is a spike of activation spreading across it, one decision every 3 nanoseconds. 100 billion decisions in 5 minutes. no queue, no waiting for anyone to press run. → lesson: the cheap, fast layer should make almost every decision. that's the whole point of it. 2. the spider: Opus 5.5 - it doesn't read the stream. it walks the brain and only goes where activity is hot. it plants its legs on the nodes, probes them and carries the result. 96 probes in 5 minutes. 4 failed and were retried. → lesson: the frontier model shouldn't see everything. it should know where to look. 3. the Dots agents: Echo, Sprout, Pocket, Stella - ingest, train, store, rank. they never touch the raw stream. they only act on what the spider brings them. 31 deliveries, every one tied to a real probe. → lesson: downstream agents work best on curated input, not raw firehose. 4. you - you read one dashboard and a summary. the math: 100,000,000,000 decisions → 96 probes → 31 deliveries → 1 screen. the question that changed how i build these: not "how smart is the model?" but "how rarely does it need to move?" i'm breaking down one AI stack like this every week. if your team still routes every decision through the biggest model, show this to whoever pays the API bill. would you trust a 3-nanosecond decision to tell your most expensive model where to look? why or why not?

deezzex

25,385 views • 2 days ago

holy sh*t. Sam Altman shows his personal dots setup one dot. one job. it works the night shift so he doesn't have to: -> reads everything that came in overnight: email, calendar, Slack, DMs -> sorts it into urgent vs can wait, based on how he likes to work -> drafts the replies and sends nothing -> checks every action against his custom rules: proceed, ask him, or hand it off -> before his day starts he gets one ping with only the urgent stuff, drafts attached -> it reaches him in ChatGPT, Slack, Teams or by call -> whatever he edits or ignores goes back into memory runs 24/7 on its own cloud computer, through plug-ins he already connected how i'd copy it: > one job first > read-only for a week > sending always asks > correct it out loud included in Pro, Business Premium and Enterprise give yours the night shift tonight

holy sh*t. Sam Altman shows his personal dots setup one dot. one job. it works the night shift so he doesn't have to: -> reads everything that came in overnight: email, calendar, Slack, DMs -> sorts it into urgent vs can wait, based on how he likes to work -> drafts the replies and sends nothing -> checks every action against his custom rules: proceed, ask him, or hand it off -> before his day starts he gets one ping with only the urgent stuff, drafts attached -> it reaches him in ChatGPT, Slack, Teams or by call -> whatever he edits or ignores goes back into memory runs 24/7 on its own cloud computer, through plug-ins he already connected how i'd copy it: > one job first > read-only for a week > sending always asks > correct it out loud included in Pro, Business Premium and Enterprise give yours the night shift tonight

NO1ennn

132,160 views • 5 days ago

OpenAI CEO, Sam Altman: "I just tell the model what I want come back in 30 minutes and it's all ready. Astra is the first model where I could tell someone just give it a try and it will work." In 20 minutes he explains how AI went from a tool you operate to an agent that operates your computer for you, and where that goes next. Worth more than any $500 AI course you'll find. Watch it, then read the guide below on the easiest way to run your own agent team for free.

OpenAI CEO, Sam Altman: "I just tell the model what I want come back in 30 minutes and it's all ready. Astra is the first model where I could tell someone just give it a try and it will work." In 20 minutes he explains how AI went from a tool you operate to an agent that operates your computer for you, and where that goes next. Worth more than any $500 AI course you'll find. Watch it, then read the guide below on the easiest way to run your own agent team for free.

Anatoli Kopadze

116,387 views • 1 month ago

GPT-6 is one of most noticable jumps you can't argue. And 3D is where it shows the hardest. I ran it through Blender few days: assembled a whole car from primitives, rigged and animated my quadruped creature, built a stylized island town and more. The full video with every test is out. My recommendation: run it through MCP. Computer Use is more of a fun demo, but with the right MCP tools it gets close to magic. If you don't want to wait forever and burn all your tokens, use the full setup. I break down mine in the video.

GPT-6 is one of most noticable jumps you can't argue. And 3D is where it shows the hardest. I ran it through Blender few days: assembled a whole car from primitives, rigged and animated my quadruped creature, built a stylized island town and more. The full video with every test is out. My recommendation: run it through MCP. Computer Use is more of a fun demo, but with the right MCP tools it gets close to magic. If you don't want to wait forever and burn all your tokens, use the full setup. I break down mine in the video.

Stefan 3D AI

41,116 views • 1 month ago

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

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 views • 1 month ago

OpenAI Dots is f*cking insane for building a 24/7 AI company... here's a one-person company architecture to build around it: one founder. five workstreams. one connected operating loop 01 research customer signals + documents → a source-backed brief with the evidence behind each decision 02 product the brief + recurring feedback → scoped changes, tested code and PRs ready for review 03 content product updates + your voice → launch materials, clips and social drafts 04 sales account history + customer requirements → proposals, proof-of-concept work and a test plan 05 operations business records + open commitments → prepared invoices, follow-up drafts and work ready for approval the useful part is how the branches connect: research shapes the product. product changes feed content. sales requirements feed testing. your corrections improve the next run the loop: set the goal → connect the context → collect evidence → prepare the work → review and approve → feed corrections back the rollout starts with one primary dot. the five branches in this map are workstreams around it set app permissions and approval rules upfront. proactive background research uses read-only tools save this, then build your company with Dots ⭣

OpenAI Dots is f*cking insane for building a 24/7 AI company... here's a one-person company architecture to build around it: one founder. five workstreams. one connected operating loop 01 research customer signals + documents → a source-backed brief with the evidence behind each decision 02 product the brief + recurring feedback → scoped changes, tested code and PRs ready for review 03 content product updates + your voice → launch materials, clips and social drafts 04 sales account history + customer requirements → proposals, proof-of-concept work and a test plan 05 operations business records + open commitments → prepared invoices, follow-up drafts and work ready for approval the useful part is how the branches connect: research shapes the product. product changes feed content. sales requirements feed testing. your corrections improve the next run the loop: set the goal → connect the context → collect evidence → prepare the work → review and approve → feed corrections back the rollout starts with one primary dot. the five branches in this map are workstreams around it set app permissions and approval rules upfront. proactive background research uses read-only tools save this, then build your company with Dots ⭣

beamnxw ./

97,486 views • 6 days ago

This AI agent does the job of an F1 TV director, and you can see every choice it makes. It follows qualifying at the 2026 Dutch GP, with live timing and onboard cameras from every car, and picks which shots to put on screen. Here's what it runs on: a LangChain deep agent that plans each step and uses tools NVIDIA Nemotron as the model, running on Nebius Token Factory through an OpenAI-compatible API LangSmith, which records every run The LangSmith part is my favorite. You can open any run and see which model call it made, which tool it used, and how long each step took. If something goes wrong, you can find the exact step instead of guessing. Each piece comes from a different company, and you can switch any one of them for another tool without rebuilding the rest. This build is part of the Nebius AI Builder Program launch, and you can use the same pieces to build your own. Join the Nebius AI Builder Program free at $400+ in credits across the stack on day one. In collaboration with Nebius #nebiuspartnership

This AI agent does the job of an F1 TV director, and you can see every choice it makes. It follows qualifying at the 2026 Dutch GP, with live timing and onboard cameras from every car, and picks which shots to put on screen. Here's what it runs on: a LangChain deep agent that plans each step and uses tools NVIDIA Nemotron as the model, running on Nebius Token Factory through an OpenAI-compatible API LangSmith, which records every run The LangSmith part is my favorite. You can open any run and see which model call it made, which tool it used, and how long each step took. If something goes wrong, you can find the exact step instead of guessing. Each piece comes from a different company, and you can switch any one of them for another tool without rebuilding the rest. This build is part of the Nebius AI Builder Program launch, and you can use the same pieces to build your own. Join the Nebius AI Builder Program free at $400+ in credits across the stack on day one. In collaboration with Nebius #nebiuspartnership

Chidanand Tripathi

99,060 views • 14 days ago

elon musk grabbed the source code openai open-sourced by accident, rewrote it in rust over a weekend, and shipped it as a free coding agent that does everything $200/mo chatgpt pro does. why pay $200 to openai and $200 to claude when this runs for $8 the swarm above is one weekend of exactly that: thousands of agents pouring through four endpoints, three paid seats billing $1.80 a task while the free fork bills $0. musk co-founded openai, walked out, and when they left codex on github under a permissive license, he forked it, stamped grok on it, and gave it away what the free version does that the $200 seat charges for: the agent · openai's own engine -> it reads your repo, writes patches, runs your tests, and loops until they pass, exactly like codex -> because under the hood it is codex, just faster and free. you are paying $200 for the paid skin of a tool now sitting on github the license · apache-2.0, un-revocable -> free to use, free to fork, free to ship inside your own product with zero strings -> openai cannot pull it back. musk made sure the license is the kind that never expires the switch · one line, no new tools -> point it at any openai-compatible or claude-compatible endpoint, including an $8 kimi backend -> same terminal, same workflow, gpt-5.6 and opus 5 just quietly lose the seat the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the free agent plus an $8 kimi key does the same daily work -> that is a 98% cut, built out of openai's own source code, handed to you by the guy suing them here is the part they will fight me on: openai did not lose this to a better model, they lost it to their own license and an enemy with a weekend free. the $200 was never the tool, it was the toll, and musk just put openai's own logo on the road around it drop your $400/mo ai stack to $8. the run above is openai's own agent, rewritten free, doing the job it bills $200 a month for. the full breakdown is in the article below

starmex

111,684 views • 1 month ago

OpenAI just showed a system called dots that stops answering questions and starts marking where the answer would have to come from. It returns no text. It returns points on your own data, each one a place the claim is either supported or is standing on nothing. > SPREAD - the question broken into the individual claims an answer would need > ANCHOR - each claim pinned to the exact span in your documents that carries it > VOID - claims with no span behind them left empty instead of being filled in > LINK - anchors connected where one claim depends on another holding first > READ - the finished map returned as points, never as a paragraph A normal answer hides its own gaps. The sentences are smooth, and the part with nothing underneath reads identically to the rest. Dots refuses that trade. An unsupported claim shows up as an empty point, impossible to skim past. The dependency links are the sharp part. One hollow anchor exposes every claim resting on top of it at once. That turns a wrong answer into a located problem. You see which document is missing, not just that something feels off. Fluency has been doing the convincing in every tool shipped so far. Here it has nothing to hide behind. The dot format and how the voids are scored are laid out in the breakdown below.

OpenAI just showed a system called dots that stops answering questions and starts marking where the answer would have to come from. It returns no text. It returns points on your own data, each one a place the claim is either supported or is standing on nothing. > SPREAD - the question broken into the individual claims an answer would need > ANCHOR - each claim pinned to the exact span in your documents that carries it > VOID - claims with no span behind them left empty instead of being filled in > LINK - anchors connected where one claim depends on another holding first > READ - the finished map returned as points, never as a paragraph A normal answer hides its own gaps. The sentences are smooth, and the part with nothing underneath reads identically to the rest. Dots refuses that trade. An unsupported claim shows up as an empty point, impossible to skim past. The dependency links are the sharp part. One hollow anchor exposes every claim resting on top of it at once. That turns a wrong answer into a located problem. You see which document is missing, not just that something feels off. Fluency has been doing the convincing in every tool shipped so far. Here it has nothing to hide behind. The dot format and how the voids are scored are laid out in the breakdown below.

wast3

86,189 views • 6 days ago

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

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 views • 8 days ago

OpenAI just showed a system called dots that stops answering questions and starts marking where the answer would have to come from. It returns no text. It returns points on your own data, each one a place the claim is either supported or is standing on nothing. > SPREAD - the question broken into the individual claims an answer would need > ANCHOR - each claim pinned to the exact span in your documents that carries it > VOID - claims with no span behind them left empty instead of being filled in > LINK - anchors connected where one claim depends on another holding first > READ - the finished map returned as points, never as a paragraph A normal answer hides its own gaps. The sentences are smooth, and the part with nothing underneath reads identically to the rest. Dots refuses that trade. An unsupported claim shows up as an empty point, impossible to skim past. The dependency links are the sharp part. One hollow anchor exposes every claim resting on top of it at once. That turns a wrong answer into a located problem. You see which document is missing, not just that something feels off. Fluency has been doing the convincing in every tool shipped so far. Here it has nothing to hide behind. The dot format and how the voids are scored are laid out in the breakdown below.

OpenAI just showed a system called dots that stops answering questions and starts marking where the answer would have to come from. It returns no text. It returns points on your own data, each one a place the claim is either supported or is standing on nothing. > SPREAD - the question broken into the individual claims an answer would need > ANCHOR - each claim pinned to the exact span in your documents that carries it > VOID - claims with no span behind them left empty instead of being filled in > LINK - anchors connected where one claim depends on another holding first > READ - the finished map returned as points, never as a paragraph A normal answer hides its own gaps. The sentences are smooth, and the part with nothing underneath reads identically to the rest. Dots refuses that trade. An unsupported claim shows up as an empty point, impossible to skim past. The dependency links are the sharp part. One hollow anchor exposes every claim resting on top of it at once. That turns a wrong answer into a located problem. You see which document is missing, not just that something feels off. Fluency has been doing the convincing in every tool shipped so far. Here it has nothing to hide behind. The dot format and how the voids are scored are laid out in the breakdown below.

wast3

62,117 views • 4 days ago

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

MIKE

26,662 views • 3 months ago