•twitter15877
listening to
timeline
15877
mentions
tracked
tracked
net sentiment
+24%
4998 positive
9734 neutral
1145 negative
volume & sentiment over time
Sep 30 – Oct 14, 2026 · Daily
sources
most discussed
—
active days
15
mentions
Showing 4001–4025 of 4998 mentions
-
• twitter 1w positiveMade a presentation recently for a few meetups on how I create @pidotdev extensions (and how you can too!) A 4 part short video series on it (because a great presentation should not go to waste!) Part 1: What is inside the coding harness? (you can skip to Part 2) https://t.co/valhzXFL3b Made a presentation recently for a few meetups on how I create @pidotdev extensions (and how you can too!) A 4 part short video series on it (because a great presentation should not go to waste!) Part 1: What is inside the coding harness? (you can skip to Part 2) https://t.co/valhzXFL3bview source ↗
-
• twitter 1w positiveSetting up your Hermes with Discord should now be a little less confusing or painful https://t.co/4zncWcOfF8 Setting up your Hermes with Discord should now be a little less confusing or painful https://t.co/4zncWcOfF8view source ↗
-
• twitter 1w positiveSkillscout: my free Mac app to keep track of the skills my coding agents use https://t.co/QzS43rvEC6 Skillscout: my free Mac app to keep track of the skills my coding agents use https://t.co/QzS43rvEC6view source ↗
-
• twitter 1w positiveRashmika's point actually made a lot of sense to me. A relationship doesn't stay strong just because two people love each other. It survives because both people keep putting in the small efforts every single day. And the way Vijay said Rashmika reminds him to say "I love you" and never stop doing the little things...… Rashmika's point actually made a lot of sense to me. A relationship doesn't stay strong just because two people love each other. It survives because both people keep putting in the small efforts every single day. And the way Vijay said Rashmika reminds him to say "I love you" and never stop doing the little things... that's probably why their bond feels so genuine. Sometimes it's really the small things that keep a relationship alive.view source ↗
-
• twitter 1w positiveOne day ends. Another begins. New chances arrive. Your best moments are ahead of you. One day ends. Another begins. New chances arrive. Your best moments are ahead of you.view source ↗
-
• twitter 1w positiveIs this the best player in college football right now? https://t.co/RuiOtJMQHU Is this the best player in college football right now? https://t.co/RuiOtJMQHUview source ↗
-
• twitter 1w positiveNFL MVP breaks down one of the most important lessons on fear you will ever hear 🙏🌏💫❤️ https://t.co/XQcQMsAKMt NFL MVP breaks down one of the most important lessons on fear you will ever hear 🙏🌏💫❤️ https://t.co/XQcQMsAKMtview source ↗
-
• twitter 1w positiveI feel like I’m frying my dopamine system with all this Claude/Codex work. Constantly monitoring and instructing, anticipating the work it’s going to produce. Then killing time waiting, consuming way more algo feed content than ever before. How do y’all tackle this? I feel like I’m frying my dopamine system with all this Claude/Codex work. Constantly monitoring and instructing, anticipating the work it’s going to produce. Then killing time waiting, consuming way more algo feed content than ever before. How do y’all tackle this?view source ↗
-
• twitter 1w positiveMore scared of AI-native kids than AI taking my job. He’s 16 and this is probably the best use of our SDK I’ve seen so far. More scared of AI-native kids than AI taking my job. He’s 16 and this is probably the best use of our SDK I’ve seen so far.view source ↗
-
• twitter 1w positiveAnthropic cookbook worth checking out... a code reviewer that runs on a schedule and remembers its last review The first run reviews the whole repo. Every run after that resumes the previous session, so it starts with its past findings loaded and reports what got fixed, what's still open, and what's new Persistent me… Anthropic cookbook worth checking out... a code reviewer that runs on a schedule and remembers its last review The first run reviews the whole repo. Every run after that resumes the previous session, so it starts with its past findings loaded and reports what got fixed, what's still open, and what's new Persistent memory across runs, no external store needed - Model pinned, so reviews stay consistent when the default model changes - SDK Claude Agent SDK with session resume - Tools Read, Glob and Grep only, no write access - Guardrails dontAsk permission mode, max turns and a USD budget cap - Output JSON schema with a verdict and findings - Scheduler plain cron You could also do this with Claude Code Routines or Claude Managed Agents, but this notebook shows you how to run it on your own infra with the Agent SDK https://t.co/H3jmg6l4Sgview source ↗
-
• twitter 1w positiveTesla FSD feels like magic Tesla FSD feels like magicview source ↗
-
• twitter 1w positiveCLACKY 2.0 IS OUT 🥹🎉 🔥 last 25 lifetime licences at $4.99 → https://t.co/2zMNvEFkDv not just clicks anymore 👀 EVERY mac tool you need: 🎥 screen recorder + auto captions 📝 teleprompter (invisible in recordings) 📸 screenshot studio 🩺 mac health + storage cleanup 🤖 alerts when claude / codex is done 🎧 focus modes + ke… CLACKY 2.0 IS OUT 🥹🎉 🔥 last 25 lifetime licences at $4.99 → https://t.co/2zMNvEFkDv not just clicks anymore 👀 EVERY mac tool you need: 🎥 screen recorder + auto captions 📝 teleprompter (invisible in recordings) 📸 screenshot studio 🩺 mac health + storage cleanup 🤖 alerts when claude / codex is done 🎧 focus modes + keep awake ⌨️ and yes… the clicks +new updates boop made some NEW friends 🐣 after the 25, it's a subscription ⏳view source ↗
-
• twitter 1w positiveGoogle had almost every ingredient to dominate AI: - the browser - the mobile OS - the search engine - decades of user intent - enormous infrastructure - one of the richest data ecosystems on earth Yet Gemini still feels like it’s chasing Claude and GPT. How does the company with that head start end up behind? Google had almost every ingredient to dominate AI: - the browser - the mobile OS - the search engine - decades of user intent - enormous infrastructure - one of the richest data ecosystems on earth Yet Gemini still feels like it’s chasing Claude and GPT. How does the company with that head start end up behind?view source ↗
-
• twitter 1w positive🚨 𝟱𝗛𝗥𝗦 𝗟𝗘𝗙𝗧 & 𝗦𝗣𝗢𝗧𝗦 𝗙𝗜𝗟𝗟𝗜𝗡𝗚 𝗙𝗔𝗦𝗧! 𝗖𝗟𝗔𝗜𝗠 𝗬𝗢𝗨𝗥 𝗙𝗥𝗘𝗘 𝗙𝗨𝗟𝗟 𝗙𝗨𝗡𝗡𝗘𝗟 𝗕𝗨𝗜𝗟𝗗 𝗔𝗡𝗗 𝗧𝗨𝗥𝗡 𝗩𝗜𝗘𝗪𝗦 𝗜𝗡𝗧𝗢 𝗜𝗡𝗤𝗨𝗜𝗥𝗜𝗘𝗦, 𝗡𝗢𝗧 𝗟𝗜𝗞𝗘𝗦. 𝗚𝗢𝗡𝗘 𝗧𝗢𝗡𝗜𝗚𝗛𝗧. 🚨 → https://t.co/Ppmk5h9rw3 🚨 𝗩𝗜𝗘𝗪𝗦 𝗪𝗜𝗧𝗛 𝗡𝗢 𝗦𝗜𝗧𝗘 𝗚𝗢 𝗡𝗢𝗪𝗛𝗘𝗥𝗘. 𝗢𝗡𝗘 𝗖𝗟𝗔𝗨𝗗𝗘 𝗣𝗥𝗢𝗠𝗣𝗧 𝗕𝗨𝗜𝗟𝗗𝗦 𝗧𝗛𝗘 𝗦𝗜𝗧𝗘 𝗔𝗟𝗟 𝗬𝗢𝗨𝗥 𝗖𝗢𝗡𝗧𝗘𝗡𝗧 𝗣𝗢𝗜𝗡𝗧𝗦 𝗧𝗢. 𝗡𝗢 𝗗𝗘𝗦𝗜𝗚𝗡𝗘𝗥. 𝗡𝗢 𝗗𝗘𝗩𝗘𝗟𝗢𝗣𝗘𝗥. 𝗡𝗢 𝗪𝗔𝗜𝗧𝗜𝗡𝗚 𝗢𝗡 𝗔𝗡𝗬𝗢𝗡𝗘. 🚨 → https://t.co/Ppmk5… 🚨 𝟱𝗛𝗥𝗦 𝗟𝗘𝗙𝗧 & 𝗦𝗣𝗢𝗧𝗦 𝗙𝗜𝗟𝗟𝗜𝗡𝗚 𝗙𝗔𝗦𝗧! 𝗖𝗟𝗔𝗜𝗠 𝗬𝗢𝗨𝗥 𝗙𝗥𝗘𝗘 𝗙𝗨𝗟𝗟 𝗙𝗨𝗡𝗡𝗘𝗟 𝗕𝗨𝗜𝗟𝗗 𝗔𝗡𝗗 𝗧𝗨𝗥𝗡 𝗩𝗜𝗘𝗪𝗦 𝗜𝗡𝗧𝗢 𝗜𝗡𝗤𝗨𝗜𝗥𝗜𝗘𝗦, 𝗡𝗢𝗧 𝗟𝗜𝗞𝗘𝗦. 𝗚𝗢𝗡𝗘 𝗧𝗢𝗡𝗜𝗚𝗛𝗧. 🚨 → https://t.co/Ppmk5h9rw3 🚨 𝗩𝗜𝗘𝗪𝗦 𝗪𝗜𝗧𝗛 𝗡𝗢 𝗦𝗜𝗧𝗘 𝗚𝗢 𝗡𝗢𝗪𝗛𝗘𝗥𝗘. 𝗢𝗡𝗘 𝗖𝗟𝗔𝗨𝗗𝗘 𝗣𝗥𝗢𝗠𝗣𝗧 𝗕𝗨𝗜𝗟𝗗𝗦 𝗧𝗛𝗘 𝗦𝗜𝗧𝗘 𝗔𝗟𝗟 𝗬𝗢𝗨𝗥 𝗖𝗢𝗡𝗧𝗘𝗡𝗧 𝗣𝗢𝗜𝗡𝗧𝗦 𝗧𝗢. 𝗡𝗢 𝗗𝗘𝗦𝗜𝗚𝗡𝗘𝗥. 𝗡𝗢 𝗗𝗘𝗩𝗘𝗟𝗢𝗣𝗘𝗥. 𝗡𝗢 𝗪𝗔𝗜𝗧𝗜𝗡𝗚 𝗢𝗡 𝗔𝗡𝗬𝗢𝗡𝗘. 🚨 → https://t.co/Ppmk5h9rw3 🚨 𝟱 𝗛𝗢𝗨𝗥𝗦. 𝗦𝗣𝗢𝗧𝗦 𝗙𝗜𝗟𝗟𝗜𝗡𝗚. 𝗖𝗟𝗔𝗜𝗠𝗘𝗗 𝗢𝗥 𝗠𝗜𝗗𝗡𝗜𝗚𝗛𝗧 𝗣𝗔𝗖𝗜𝗙𝗜𝗖. 🚨 → https://t.co/Ppmk5h9rw3 Spots filling. 5 hours left. Here's where most people's marketing quietly breaks. They finally get the content going. People watch. People like. People comment. And then... nothing. No inquiries. No calls. No sales. There's nowhere for the attention to go. Views with no site go nowhere. And a like doesn't pay your bills. Step 2 of the Full Funnel Build fixes that, with no designer. One Claude prompt builds the site all that content points to. Every video and every post sends people to one place, and that place turns a view into an inquiry instead of a like. You don't wait on a freelancer. You don't learn web design. You describe what you want in plain English in the Agent OS chat, the agents build it, and you tweak it with a bit of back and forth until it's right. Pair that with Step 1 and your feed isn't just alive anymore. It's sending people somewhere that captures them. That's the difference between content that looks busy and content that brings in work. 5 hours. Spots filling. 👉 Turn views into inquiries. Claim your build → https://t.co/Ppmk5h9rw3 🎯 𝗧𝗛𝗘 𝗙𝗨𝗟𝗟 𝗙𝗨𝗡𝗡𝗘𝗟 𝗕𝗨𝗜𝗟𝗗 (𝗙𝗥𝗘𝗘 𝗙𝗢𝗥 𝗧𝗛𝗘 𝗙𝗜𝗥𝗦𝗧 𝟱): ✅ Step 1: Get seen ... one product photo becomes UGC videos, carousels, and stories, posted by Blotato the moment you approve ✅ Step 2: Get the lead ... one Claude prompt builds the site all your content points to ✅ Step 3: Get paid ... AI follow-up answers new leads, chases quiet quotes, nudges late invoices, rebooks no-shows 💎 𝗬𝗢𝗨𝗥 𝗦𝗘𝗔𝗧 𝗖𝗢𝗩𝗘𝗥𝗦 𝗧𝗛𝗘 𝗥𝗘𝗦𝗧: ✅ The Agent OS zip file, ready to install, with the 30-day roadmap ✅ 4 live calls a weview source ↗
-
• twitter 1w positiveOrganic content has a natural ceiling at $1-3M ARR Here's how to break through it: Use organic as fuel for paid 1. Run your viral organic videos as paid ads They already proved they work. Scale what converts 2. Take hooks that performed well organically and attach them to normal ad creative You know the hook works. … Organic content has a natural ceiling at $1-3M ARR Here's how to break through it: Use organic as fuel for paid 1. Run your viral organic videos as paid ads They already proved they work. Scale what converts 2. Take hooks that performed well organically and attach them to normal ad creative You know the hook works. Now give it budget 3. Pick creators who performed well organically and have them record UGC for your paid campaigns Organic creators are better than 90% of traditional UGC talent. They're trained by the algorithm. Better hooks. Doesn't feel like ads The advantage: you get to double dip Organic converts, then the same content converts again in paidview source ↗
-
• twitter 1w positiveto make the best video ever in SF, i edited 100+ hours for a single episode you’ll enjoy it https://t.co/aCcXoDkLc7 to make the best video ever in SF, i edited 100+ hours for a single episode you’ll enjoy it https://t.co/aCcXoDkLc7view source ↗
-
• twitter 1w positiveyeah so ai is telling people what they want to hear it's very concerning anyway, types are very important for agents they give them the right feedback loop and you get better results yeah so ai is telling people what they want to hear it's very concerning anyway, types are very important for agents they give them the right feedback loop and you get better resultsview source ↗
-
• twitter 1w positive3 diff friends today send me great visual animation sequences for something they are working on right now, none of them could do this on their own before AI, another friend is working on a game, wasn’t doing this before, several friends staying home to keep working through these new projects in a Saturday night. Just i… 3 diff friends today send me great visual animation sequences for something they are working on right now, none of them could do this on their own before AI, another friend is working on a game, wasn’t doing this before, several friends staying home to keep working through these new projects in a Saturday night. Just interesting.view source ↗
-
• twitter 1w positiveWhen growth slows down, our first instinct is: “Let’s spend more on marketing.” But sometimes the real question is: “Why aren’t the people who already found us choosing us?” Maybe the message is unclear. Maybe the experience feels complicated. Maybe trust hasn’t been earned yet. Before buying more attention, mak… When growth slows down, our first instinct is: “Let’s spend more on marketing.” But sometimes the real question is: “Why aren’t the people who already found us choosing us?” Maybe the message is unclear. Maybe the experience feels complicated. Maybe trust hasn’t been earned yet. Before buying more attention, make better use of the attention you already have.view source ↗
-
• twitter 1w positiveAnother look at Blyth AI Mobile. I’m really happy with the overall design so far. There are still a few details I’m refining before release, but we’re getting close. What would you change or improve? Any feedback is welcome. https://t.co/L1Ybpd7rEc Another look at Blyth AI Mobile. I’m really happy with the overall design so far. There are still a few details I’m refining before release, but we’re getting close. What would you change or improve? Any feedback is welcome. https://t.co/L1Ybpd7rEcview source ↗
-
• twitter 1w positiveit's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior. pstack 0.15.9 now ships a new /correct skill: if you keep correcting agents for the same mistakes, it finds the pattern and fixes it with architecture, types, and checks. i like to imagine tha… it's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior. pstack 0.15.9 now ships a new /correct skill: if you keep correcting agents for the same mistakes, it finds the pattern and fixes it with architecture, types, and checks. i like to imagine that commits rapidly flowing into the codebase are like a bonsai tree rapidly growing in whatever direction it pleases. what you want to do is not to give in to the chaos, but tame it intentionally with the right constraints 0.15.9 also has improvements to: • /architect: now includes instructions on designing agent friendly architecture • a new /benchmark-checklist skill based on @brendangregg's benchmarking checklist here's a prompt you can give to grok bot to start architecting a better codebase with pstack: /poteto-mode create a new Project agent to refactor and rearchitect my repo so that our architecture is more agent friendly. it should use both the /correct and /architect skill to look through past commits and find the most common pitfalls that agents fall into, whether its with code quality, performance, or bugs. if relevant you can also use the /recall skill to find past conversations for context. it should make a high level plan for me to review. it should also answer its own open questions by prototyping rather than defer to me. come back to me with a plan backed by real data. once i approve the plan, use either the stack or full autopilot playbook (ask me which i want) to executeview source ↗
-
• twitter 1w positivewe're in the third phase of AI for business phase 1: chat chatgpt and claude. you ask, it answers phase 2: connected chat connectors, integrations, a bit of memory. it can see your stuff phase 3: agents with their own computer openclaw was first. then grok bot, muse, and now openai's dots tool calls, computer use, … we're in the third phase of AI for business phase 1: chat chatgpt and claude. you ask, it answers phase 2: connected chat connectors, integrations, a bit of memory. it can see your stuff phase 3: agents with their own computer openclaw was first. then grok bot, muse, and now openai's dots tool calls, computer use, learning your business over time, and taking actions for you this is openclaw going mainstream phase 4 is next: the multiplayer AI workspace your team and your agents in one platform, working on the same stuff together openai's space is the first look at it. people, chatgpt and dots building on shared knowledge the gap is the agents. one dot per person for now. openai showed specialist dots for roles like invoice processing, procurement and support, but they're enterprise pilots I've been building this by hand for my client builds: - the agents live in the team's slack, where the work already happens - every step that leaves the building gets a human approval - one always-on agent for the daily work, and a coding agent for building the software the labs are about to make that the default the businesses that already know which roles to hand off will move fastestview source ↗
-
• twitter 1w positive5 AM Good morning developers! 👨💻☕ 5 AM Good morning developers! 👨💻☕view source ↗
-
• twitter 1w positiveExciting to see this launch! ⭐️ What decision-makings are you already implementing in real projects? 🎉 Exciting to see this launch! ⭐️ What decision-makings are you already implementing in real projects? 🎉view source ↗
-
• twitter 1w positiveWhat are you building? 🧠 AI 🚀 SaaS 📱 Mobile 🌐 Web 🛠️ Dev tools 🎨 Design Reply with your category and one line 👇 https://t.co/ofJIeEOhwB What are you building? 🧠 AI 🚀 SaaS 📱 Mobile 🌐 Web 🛠️ Dev tools 🎨 Design Reply with your category and one line 👇 https://t.co/ofJIeEOhwBview source ↗