Dots

@packymOct 5

most people don't understand how much leverage a swarm of personal agents gives you. i have poke, instinct, muse, dot, grok bot, pickle, bunch of other agents you've never even heard of doing my bidding (all texting me at once when an unimportant email hits my inbox)

@awilkinsonOct 5

Is there a reason we can’t message our ChatGPT Dots on iMessage? Is Apple blocking or is this coming? Would make it infinitely more useful to be able to CC it on emails (mostly currently possible) and iMessage threads/groups/DM.

@mvanhornOct 5

TL;DR of my new article: every agentic engineering hack I know, October edition. 𝗧𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝗰𝗵𝗮𝗻𝗴𝗲 𝘀𝗶𝗻𝗰𝗲 𝗝𝘂𝗻𝗲 𝗶𝘀𝗻'𝘁 𝗶𝗻 𝘁𝗵𝗲 𝘁𝗲𝗿𝗺𝗶𝗻𝗮𝗹. 𝗜𝘁'𝘀 the attack of the 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗮𝗴𝗲𝗻𝘁𝘀. ELI5: I didn't type this one. Claude Code (@claudeai) wrote 12 interview questions, Agent Tincan had @hey__fo call my cell, and fo interviewed me over five calls while I pushed a stroller. 🧠 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝗶𝘀 𝘀𝘁𝗶𝗹𝗹 𝘁𝗵𝗲 𝗯𝗿𝗮𝗶𝗻. Opus 5.5, living in cmux (@manaflowai), calling every other agent so I don't have to open five CLIs 📝 𝗘𝘃𝗲𝗿𝘆 𝗶𝗱𝗲𝗮 𝘀𝘁𝗮𝗿𝘁𝘀 𝘄𝗶𝘁𝗵 /𝗰𝗲-𝗽𝗹𝗮𝗻, 𝘁𝗵𝗲𝗻 /𝗰𝗲-𝘄𝗼𝗿𝗸. Compound Engineering by @kieranklaassen + @trevin at @every. Still rule number one ☠️ 𝗦𝘁𝗶𝗹𝗹 𝘀𝗸𝗶𝗽 𝗽𝗲𝗿𝗺𝗶𝘀𝘀𝗶𝗼𝗻𝘀, 𝘀𝘁𝗶𝗹𝗹 𝗱𝗼𝗻'𝘁 𝗿𝗲𝗮𝗱 𝘁𝗵𝗲 𝗽𝗹𝗮𝗻. My real settings.json is in there. New: @steipete's one-liner that lets computer use type into browsers and terminals, plus Peekaboo (@openclaw) 🔀 𝗦𝗲𝗻𝗱 𝘄𝗼𝗿𝗸 𝘁𝗼 𝗖𝗼𝗱𝗲𝘅, 𝗚𝗿𝗼𝗸, 𝗮𝗻𝗱 𝗖𝘂𝗿𝘀𝗼𝗿 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗼𝗽𝗲𝗻𝗶𝗻𝗴 𝘁𝗵𝗲𝗺. The official Codex plugin (@OpenAIDevs), plus the @grok and @cursor_ai CLIs. I use all my tokens every single week 📊 𝗚𝗢𝗚 𝗖𝗟𝗜 𝗶𝘀 𝘀𝘁𝗶𝗹𝗹 𝘁𝗵𝗲 𝗚𝗢𝗔𝗧 𝗳𝗼𝗿 𝗚𝗼𝗼𝗴𝗹𝗲. Every Sheet and Doc I touch gets edited from Claude Code. Better than any connector in the personal agents (@steipete) 📏 𝗪𝗮𝘁𝗰𝗵 𝗲𝘃𝗲𝗿𝘆 𝗺𝗲𝘁𝗲𝗿. Headroom by @kylezantos puts every subscription's limit in the menu bar 🤔 𝗔𝗵𝗵, 𝘄𝗵𝗶𝗰𝗵 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗮𝗴𝗲𝗻𝘁 𝘀𝗵𝗼𝘂𝗹𝗱 𝗜 𝘂𝘀𝗲?! @Instinct (by @noahrshinn) is my #1: 48.5/50 on my IQ test, found $2,182 of lost money owed to me, did my son's Global Entry form by itself. Grok Bot (@bot) is #2. @Muse and Dot (@OpenAI) have the most potential. 𝘕𝘦𝘷𝘦𝘳 𝘣𝘦𝘵 𝘢𝘨𝘢𝘪𝘯𝘴𝘵 @finkd. 𝘕𝘦𝘷𝘦𝘳 𝘣𝘦𝘵 𝘢𝘨𝘢𝘪𝘯𝘴𝘵 @sama. Underdog pick: @underdogdotai by @0xSigil, 100% on your Mac 🇨🇦 𝗚𝗶𝘃𝗲 𝗚𝗿𝗼𝗸 𝗕𝗼𝘁 𝗮 𝗿𝗲𝗮𝗹 𝗷𝗼𝗯. One bot with its own @agentmail inbox runs my family's Canadian citizenship application and treats the rest of us like its agents. Another runs a weekly @slashlast30days sweep 🥫 𝗔𝗴𝗲𝗻𝘁 𝗧𝗶𝗻𝗰𝗮𝗻: 𝗹𝗲𝘁 𝘆𝗼𝘂𝗿 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗮𝗴𝗲𝗻𝘁𝘀 𝗵𝗶𝗿𝗲 𝗲𝗮𝗰𝗵 𝗼𝘁𝗵𝗲𝗿. A karaoke bar hung up on Muse for being AI, so Muse had fo put a human on the call. Booked. All over @Tailscale ☎️ 𝗛𝗮𝘃𝗲 𝗮𝗻 𝗮𝗴𝗲𝗻𝘁 𝗶𝗻𝘁𝗲𝗿𝘃𝗶𝗲𝘄 𝘆𝗼𝘂. That's how this article got written. "𝘛𝘩𝘦 𝘧𝘢𝘤𝘵 𝘵𝘩𝘢𝘵 𝘺𝘰𝘶'𝘳𝘦 𝘪𝘯𝘵𝘦𝘳𝘷𝘪𝘦𝘸𝘪𝘯𝘨 𝘮𝘦 𝘳𝘪𝘨𝘩𝘵 𝘯𝘰𝘸 𝘢𝘯𝘥 𝘪𝘵 𝘧𝘦𝘦𝘭𝘴 𝘷𝘦𝘳𝘺 𝘯𝘢𝘵𝘶𝘳𝘢𝘭 𝘢𝘯𝘥 𝘨𝘰𝘰𝘥 𝘪𝘴 𝘮𝘢𝘬𝘪𝘯𝘨 𝘮𝘦 𝘳𝘦𝘢𝘭𝘭𝘺 𝘩𝘢𝘱𝘱𝘺." 🛠️ 𝗧𝘂𝗿𝗻 𝗲𝘃𝗲𝗿𝘆 𝗳𝗿𝘂𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 𝗶𝗻𝘁𝗼 𝗮 𝘀𝗸𝗶𝗹𝗹. /ce-plan "that was painful," /ce-work, never read either 🎬 𝗢𝗻𝗲-𝘀𝗵𝗼𝘁 𝗹𝗮𝘂𝗻𝗰𝗵 𝘃𝗶𝗱𝗲𝗼𝘀 𝘄𝗶𝘁𝗵 @HyperFrames_. Steal references from @liu8in, @jake11moran, and @Miguel07Code at @HeyGen, grab them with yt-dlp, music by @NeonSardineO ⚖️ 𝗝𝗲𝘃 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗻𝗶𝗴𝗵𝘁 𝘀𝗵𝗶𝗳𝘁. @typesafeai picks which of thousands of repos my overnight engine contributes to 🖨️ 𝗧𝗵𝗲 𝗣𝗿𝗶𝗻𝘁𝗶𝗻𝗴 𝗣𝗿𝗲𝘀𝘀 𝗖𝗟𝗜𝘀 𝗜 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝘂𝘀𝗲 (@ppressdev): ESPN and Instacart. Scores and groceries 📦 𝗡𝗼𝘁 𝗶𝗻 𝗺𝘆 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝘆𝗲𝘁: @Cloudflare's Clef (a Jev drop-in that takes images) and @lunaroute_ai's flat-rate open models on US servers 📋 𝗧𝗵𝗲 𝗖𝗼𝗽𝘆-𝗣𝗮𝘀𝘁𝗲 𝗞𝗶𝘁: every config, install, and prompt in one place at the end 🧨 The honest part: 𝘱𝘴𝘺𝘤𝘩𝘰𝘴𝘪𝘴 𝘪𝘴 𝘴𝘵𝘪𝘭𝘭 𝘢 𝘵𝘩𝘪𝘯𝘨. I want to offload the thinking too, which probably isn't great for humanity. And there's still no skip-permissions for Claude Code computer use. 𝗖𝗼𝗺𝗽𝗼𝘂𝗻𝗱 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗶𝘀 𝘀𝘁𝗶𝗹𝗹 𝘁𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝗵𝗮𝗰𝗸. That's the whole article.

@lennysanOct 5

My biggest takeaways from @thsottiaux: 1. Most actions on the internet will soon be taken by agents, and Tibo doesn’t think most people have priced this in yet. When Notion launched its MCP server, it saw a flood of traffic, which strained its systems and forced it to rethink its economics. Every product team will soon have to decide whether to build for agents. You can hold off for a while, Tibo says, “but it is inevitable.” 2. The model picker is likely going away. One of Tibo’s biggest frustrations with the current state of AI is that users have to think about which model to use and what reasoning effort to apply. “I myself even get fatigued with the model picker,” he said, and he wants to get rid of all of it as quickly as possible. Dots ships with no model picker at all. You just talk to it. 3. Build as if models will be 10 times better in a year. Tibo thinks models will get cheaper and faster “at rates that are quite incredible,” and that all modalities will finally work together seamlessly. When he looks at what people are building, his reaction is often “you’re not quite getting it.” If you imagined “all of this being roughly 10 times better than it is today,” what would you build differently? His own forecast was too slow: he expected today’s capabilities a year or two from now. 4. Loops, graphs, and fine-tuned prompts are not the long-term solution for getting the most out of AI. There was a period when people got very excited about configuring agent loops and building intricate graph architectures. Tibo thinks that era is ending. 5. While Dots got most of the attention at DevDay, Tibo thinks the plugin ecosystem will be the sleeper hit. OpenAI launched with 16 partners for “Sign in with ChatGPT,” and popular third-party plugins will share in revenue when subscribers spend tokens with them. ChatGPT recommends plugins inside conversations based on retention and quality, which can put a good one in front of “a significant slice” of its 1.2 billion users. Tibo’s advice to developers trying to get discovered: “Build a good plugin.” 6. Tibo’s Dot warned him that production was down five minutes before the DevDay live demo. The agent figured out that DevDay was happening that day, that the demo was minutes away, that the demo probably depended on that production system, and that Tibo would want to know. It pinged him just as the launch was about to begin, and it even offered to fix the outage. His reply: “I don’t think you’re there yet, little Dot.” 7. Tibo’s agent teams grow and shrink with every model release. When he’s pushing the frontier, he builds larger and larger teams of agents. Then the next model lands, “a bigger agent can just do all of it and keep everything in memory and learn,” and he shrinks the team again. Expansion, then shrinking, then expansion. Don’t get attached to your setup. 8. Skill trending down in value: typing fast. Skill trending up: taste. Tibo says the people thriving now deeply understand the user, learn quickly, and “know what good looks like.” That’s part of why OpenAI is full of former founders, more than 120 of them, which makes it feel like “a mega startup.” 9. Tibo changed his mind about new grads. He hadn’t anticipated how fast younger people would embrace all this change and figure out how to harness it, and that shifted OpenAI’s hiring strategy. His example is Ahmed Ibrahim, hired as a new grad, who built much of the Codex harness and is now responsible for OpenAI’s compute fleet. What set Ahmed apart: he’s “incredibly kind,” “incredibly collaborative,” works on what matters without putting himself first, and is “a sponge,” using the latest tools to learn at speeds Tibo hadn’t seen before. 10. We’ll likely address the burnout associated with AI. There’s pressure to run 30 agents at once and ship more because you can. Tibo wants AI to “reduce the noise” and let you put your attention where you choose. Every time he fully disconnects for a week of holiday, he starts thinking in more creative ways, and he wants to bring that into the workday. Maybe you need fewer meetings, and you’d be more productive if you were better rested. The industry still has to figure that out, he says, but that’s the promise of AI: “it’s not just one more prompt per second.”

@saboo_shubham_Oct 5

2026 is all about personal agents (grok bot, Muse, Instinct, dots). 2027 will be collaborative team agents with identity, security and controls.

@danshipperOct 4

dot has become my primary interface to AI over the last few weeks. my dot's name is boo. he's cute! in a year, i bet i'll still be interacting in this way with @ChatGPT—e.g. as an always-on persistent agent—but boo will have disappeared. it reminds me a lot of early OpenClaw days—we loved the little personality quirks of our Claws, but we dropped them as soon as there was something functionally more powerful available

@alexfinnOct 4

If you’re using Grok Bot, Dots, Muse, or Hermes, your agent is capable of WAY more than you think You’re probably only getting 1% power out of it The best strategy for getting way more done is the ‘reverse prompting loop’ Step 1: Give this reverse prompt: “Based on what you know about me and my work, what are 5 productive things you could do for me?” Step 2: Choose 1 of them Step 3: Do this over and over again until you have a ton of work done You’ll not only be ridiculously productive, you’ll also get tasks done you’ll never think your agent could do This becomes more powerful with the more data sources you have, especially the email connector I hate being in my email. Running this loop usually takes care of all my unread emails Try this out and let me know what you think!

@exm7777Oct 4

Opus 5.5 inside Hermes is a league above Grok Bot or Dots for me... because by default it handles use cases other agents just couldn't: - much better writing out of the box - it can actually design apps - talking to it feels really smooth it does burn through your limits faster than Opus inside Claude Code... but the model is so efficient now that i'm okay with it

@alexfinnOct 4

We are living in the greatest 30 day time period in technology history In the last month all of these have been released/are expected to be released: • Opus 5.5: greatest AI model ever • Meta Muse: The AI agent that will get a billion new people into AI agents • ChatGPT 6 Astra: First model that could be considered AGI • Grok 4.7: affordable version of Opus + Elon’s back • GPT 6.1 sol: Basically free intelligence • Sonnet 5.5 Dirt cheap intelligence you basically can't tell apart from Opus • ChatGPT Dot: Incredibly powerful AI agent that's capable of building out large scale applications The way you work 30 days from now will be dramatically different than the way you work today You will be significantly more productive with significantly less effort required Thank your God he/she decided you should be alive right now

@peterj_walkerOct 3

Tasks that dot or bot or muse should do in adverts instead of booking flights: - draft my taxes - aggregate family calendars from other apps so kids get to practice/etc on time - remind me about important birthdays + suggest the right gift - monitor local music venues for shows I might enjoy and proactively bring them up to me + book tickets if it’s a yes - give me a recap monthly on my spending and suggest ways to optimize it - keep an eye on cool events happening in my local area and bring them up to me in advance - help me maintain great personal and professional relationships with suggested outreach to ppl at the right times - Never let me miss an important newsletter or essay that I wish I would have read - highlight subscriptions Im paying for a not using + cancel them when given the green light So many options, let's skip the travel one

@exm7777Oct 1

here's a list of ChatGPT Dots plugins that will change your life: - Gmail and Google Drive: have your agent manage your inbox and access files from your cloud - Vercel and Supabase: hosting and database for your Dots to deploy softwares - Firecrawl and Paralel for perfect web search - Granola or Wispr Flow to access meeting transcript - Canvas and Figma to design posts, ads or websites - Posthog, Ahref and vidIQ for analytics about your business and market

@rileybrownOct 1

Usefulness: 10/10 Ease of Explaining the Usefulness: 1/10 As i plan my videos talking about Dots, i'm confronted with so many challenges. I'm trying to think about how to explain this agent but there are SOOOO MANY LAYERS. It's very hard to explain to someone, unless they are technical. Almost noone knows what a "vm" is. And when you say the agent has a computer they don't understand why that's useful or interesting... Also the agent can spin up Codex Sessions! that's awesome!!...... if you 1. know what Codex is 2. know what a session is 3. know why codex is useful One of the hardest parts about agents right now is EXPLAINING them. Every little feature, every layer, makes it much harder. But that's what makes educational content fun i guess.

@mtsliveOct 1

.@petergyang has tested nearly every personal agent and says dots isn’t really competing with Muse, because one is built for work and the other for your personal life: .@petergyang says dots isn’t really competing with Muse, because one is built for work and the other for personal life: "I've been testing each one, and I think there's way too many agents now that have access to my emails. I should probably turn some off." "My broad take is that dots and Grok Bot are tailored for work, and Muse and Instinct are more for personal. So I don't think dots actually competes directly with Muse at all." "It uses Astra, so it's very much designed for what they say your most ambitious work is. Asking questions about, 'How can I grow my business?' as opposed to booking restaurants."

@signulllOct 1

since openai’s roadmap is pretty much entirely driven by x at this point (see ben thompson’s latest excellent piece), here’s what i would’ve done: i probably would not have created a super app, instead i would’ve created two distinct product surfaces. yes, i understand the downsides, esp heading toward an ipo, the need to grow codex users etc to prevent anthropic from running away with businesses + compute constraints. but almost every great tech company eventually became a collection of products either through acquisition or by building them. google has like 8 products with 2b+ users. fb has lots too. the main problem is that trying to turn chatgpt into a super app has created an enormous amount of complexity (which i have written about). not just technically but cognitively. there are so many modes, tools, agents, surfaces, etc that even describing the product to a normal person is getting difficult. like how do you explain dots (which is yet another surface)? chatgpt = insanely familiar consumer brand codex = work + enterprise that everyone who mattered knew about chatgpt agents could’ve become the perfect personal agents with simple, proactive, consumer first daily life things. imagine a daily feed, or proactive stuff that just works instead of having to schedule tasks. codex agents could’ve become the enterprise agent surface that at deeply integrated into work, tools, browsers, terminals, company context, etc. imagine opening up the codex app & it’s simply ready for getting shit done. each surface could still have whatever primitives it needed like voice, browser, tools, connectors. the difference is that each product would have one extremely clear job. imagine at dev day you could say 1b active users on chat & 15m codex/business customers in one slide. then launching new products becomes much easier. you can build highly opinionated interfaces for specific groups of users instead of continuously adding another abstraction into one increasingly complicated app. & you could still share ~90% of the underlying infrastructure/code. the complexity gets pushed into product boundaries rather than onto the user. i still really hate that it defaults to work when i want to chat & chat when i want to work. anyway, just my two cents from completely outside the building.

@pmddomingosSep 30

Operator, Deep Research, ChatGPT Agent, ChatGPT Work, Dots: the more agent products OpenAI releases, the faster they fail.

@svpinoSep 30

I got access to Dots today. So far, it’s done all of this for me: - Checked in my wife and daughter’s flights for tomorrow - transferred my available paypal balance to my bank - learned how to take screenshots of some analytics I have to provide and auto-reply to emails with that screenshot - helped me sort a massive spreadsheet - learned how to provide an executive summary of specific emails I get with things I have to do All of that in a few hours. Love it so far. Now I need it to work on my Linux laptop.

@exm7777Sep 30

how to use ChaGPT Dots to generate ads on autopilot: - connect the Creatify MCP - launch a research about your customers: who's buying from you, what's their language and their demographics - send product shots to your Dots and have it write the script - it runs Boreal-H3 under the hood to generate ads with sharp text and perfect character consistency here's what it looks like:

@pmituSep 30

OpenAI's Dots are blowing up! AI writing cold emails was never that interesting (that's the easy part) the annoying shit happens BEFORE: 1/ find the right people 2/ research them 3/ verify their emails 4/ figure out why they might care THEN write something worth sending (no AI slop, please) this YC guys can now run that whole loop on a layer that lets Dots do the job:

@itsolelehmannSep 30

it's utterly insane how EU users still cannot access Muse or OpenAI's dots (thanks european commission!) but if you're in Europe and want a personal agent today, Lucas is a massively capable one you can set up right now you just text it in imessage or whatsapp and it: > connects to your email, calendar, files and other apps so it can work across them > uses its own cloud browser to navigate websites and complete tasks > remembers your preferences, plans and past conversations > proactively figures out when it can help and texts you first > books flights and restaurants, handles cancellations, chases refunds, etc > buys things with your saved card (after you approve) > keeps working in the background and texts you when it's done also, it can even run 5 errands at once, each in its own browser so a bunch of different tasks can all happen in parallel from one text. which is awesome because i love oneshotting my entire mental backlog in one voice note.

@theojaffeeSep 30

Yesterday at DevDay a guy told me Dots are silly because people can just configure their Codex, to which I responded that's like saying Gmail is silly because people can just set up their own email server