•twitter16828
listening to
timeline
16828
mentions
tracked
tracked
net sentiment
+24%
5285 positive
10312 neutral
1231 negative
volume & sentiment over time
Sep 30 – Oct 16, 2026 · Daily
sources
most discussed
—
active days
17
mentions
Showing 12476–12500 of 16828 mentions
-
• twitter 1w positiveDot voice: what we're fixing ⚒️ We're hearing lots of great feedback on Dot voice: 1. It takes too long to connect or fails entirely (5-6 rings) 2. The phone call UX: some people love it, some don't 3. No way to see transcript or summary 4. Says "Checking" too much 5. Sometimes goes quiet and does not give updates … Dot voice: what we're fixing ⚒️ We're hearing lots of great feedback on Dot voice: 1. It takes too long to connect or fails entirely (5-6 rings) 2. The phone call UX: some people love it, some don't 3. No way to see transcript or summary 4. Says "Checking" too much 5. Sometimes goes quiet and does not give updates Here's what we're doing next: 1. Making connection fast and reliable 2. Keeping the phone call UX for now, but instant 3. Adding transcript and summaries to the UI 4. Adding more variance to "Checking" (eventually will remove it for fast questions) 5. Adding more regular updates Our goal is for Dot voice to become the chief-of-staff you can delegate any task to, hands-free. What did we miss? Please keep the feedback coming!view source ↗
-
• twitter 1w positiveIntroducing my Hermes "Alan's way". (The Grokbot killer) - Grokbot style UI using telegram API (the most consistent gateway for Hermes with built-in bot feedback and signals) - The Hermes bots live on my VM but now optimally run tasks on my macbook while it's running. 1 home for the bots with multiple workplaces - … Introducing my Hermes "Alan's way". (The Grokbot killer) - Grokbot style UI using telegram API (the most consistent gateway for Hermes with built-in bot feedback and signals) - The Hermes bots live on my VM but now optimally run tasks on my macbook while it's running. 1 home for the bots with multiple workplaces - just like grokbot. - chatGPT app-style browser and agent browser use. (I was addicted to the browser in the chatGPT app - and this is my cure) - Controllable window into the bot's virtual desktops with near-seamless handoff between local -> remote. I can shut my laptop and certain tasks will just auto route to the VM. - native proactivity mode for the lead bot so it can oversee the other bots, and consistently come up with useful things to do (24/7). It's deeper than just a skill or cron job. - its Telegram so I can message on any device and it never breaks (hard to say about other mobile app gateways). - Still works with the main production version of Hermes, as it's just a companion app and the telegram gatewy. Grokbot, Dot, Muse, or Instinct can never beat this.view source ↗
-
• twitter 1w neutralConecten un agente Hermes a un ESP32 con un micrófono y una pantallita. Ahí tienen un Alexa que funciona de verdad https://t.co/KeAYIibd5k Conecten un agente Hermes a un ESP32 con un micrófono y una pantallita. Ahí tienen un Alexa que funciona de verdad https://t.co/KeAYIibd5kview source ↗
-
• twitter 1w neutralThe Dream are up to 14 STEALS in Game 1 🤯 With another 10+ steal game, they tie the Sparks’ WNBA playoff record for the most such games... Atlanta leads heading into the 4Q on ABC 🍿 The Dream are up to 14 STEALS in Game 1 🤯 With another 10+ steal game, they tie the Sparks’ WNBA playoff record for the most such games... Atlanta leads heading into the 4Q on ABC 🍿view source ↗
-
• twitter 1w positivethe most slept on ecom affiliate play right now isn't on tiktok it's facebook specifically AI UGC pages in the health and wellness space targeting the 40-55 demographic with amish-style natural remedy content and the ones attaching glitchy ecom products to that content are quietly printing numbers most tiktok affili… the most slept on ecom affiliate play right now isn't on tiktok it's facebook specifically AI UGC pages in the health and wellness space targeting the 40-55 demographic with amish-style natural remedy content and the ones attaching glitchy ecom products to that content are quietly printing numbers most tiktok affiliates would not believe here's why it works the 40-55 facebook audience doesn't scroll with the same cynicism a 22 year old has they read captions they click links they complete purchase flows and the amish remedy angle converts specifically because it taps into something this demographic already believes that older, simpler, natural solutions work better than what big brands are selling them trust is built into the character before the offer even appears the pages running this are not new accounts they are long term pages with months of posting history, growing audiences, and compounding reach that gets stronger every single week they stay consistent this is not a flash in the pan strategy it is a traffic asset that pays you while it grows the full breakdown of how to build one is in the article below 👇view source ↗
-
• twitter 1w positiveFirst row of sponsors on https://t.co/WTCuklKHQv: sold out at the $149 launch price. The next 4 slots are $299/month. Thank you to everyone who trusted me early :) First row of sponsors on https://t.co/WTCuklKHQv: sold out at the $149 launch price. The next 4 slots are $299/month. Thank you to everyone who trusted me early :)view source ↗
-
• twitter 1w negativeI just broke up with my instinct https://t.co/cGFL4I9kfG I just broke up with my instinct https://t.co/cGFL4I9kfGview source ↗
-
• twitter 1w neutralhttps://t.co/ztl3lNQkQU https://t.co/ztl3lNQkQUview source ↗
-
• twitter 1w positiveYour coding job is shrinking. @dhh says the programmers struggling most are the ones who loved writing the code itself and never cared much what it was for. A year ago they were the bottleneck. Every idea had to go through them, and they got paid well for it. Now agents do more of that work every month. He's asking … Your coding job is shrinking. @dhh says the programmers struggling most are the ones who loved writing the code itself and never cared much what it was for. A year ago they were the bottleneck. Every idea had to go through them, and they got paid well for it. Now agents do more of that work every month. He's asking whether anyone will need a programmer at all.view source ↗
-
• twitter 1w neutralive gone from openclaw to hermes and now moved everything to grok bot grok bot is the first that clicked for me ive gone from openclaw to hermes and now moved everything to grok bot grok bot is the first that clicked for meview source ↗
-
• twitter 1w neutral11 xx, 💋 https://t.co/Xb5kWw8CXo 11 xx, 💋 https://t.co/Xb5kWw8CXoview source ↗
-
• twitter 1w neutralChatGPT product recommendations are so stupid https://t.co/l4duiVgB7h ChatGPT product recommendations are so stupid https://t.co/l4duiVgB7hview source ↗
-
• twitter 1w neutralPOV: https://t.co/eyGHyBgfVB acquired by Apple. https://t.co/kmK0Qe5800 POV: https://t.co/eyGHyBgfVB acquired by Apple. https://t.co/kmK0Qe5800view source ↗
-
• twitter 1w negativeA Jane Street quant got fired for leaking this internally, then posted it anyway paste into Claude Code tonight. This one prompt builds a regime-detection trading bot: fits a Hidden Markov Model to read calm, choppy, stressed and crash states writes a separate playbook per state, never mixes strategies switches onl… A Jane Street quant got fired for leaking this internally, then posted it anyway paste into Claude Code tonight. This one prompt builds a regime-detection trading bot: fits a Hidden Markov Model to read calm, choppy, stressed and crash states writes a separate playbook per state, never mixes strategies switches only after a new state holds the lead for several candles, so it never flip-flops on noise walks forward through real data with real costs, and refuses to ship unless it clears Sharpe 1.5 and beats buy-and-hold ends every run with one line in caps: what could blow up this account bookmark itview source ↗
-
• twitter 1w neutralIt's out 🤲🏻💅🏻 READ https://t.co/3LUPUrbHzi It's out 🤲🏻💅🏻 READ https://t.co/3LUPUrbHziview source ↗
-
• twitter 1w neutralQuiz: Using Loguru to Simplify Python Logging #python https://t.co/F5PSzjShVR Quiz: Using Loguru to Simplify Python Logging #python https://t.co/F5PSzjShVRview source ↗
-
• twitter 1w neutralThousands of Chinese token resellers are giving AI labs unauthorized access to Anthropic’s Claude, helping them distill U.S. models. Anthropic’s crackdown is pushing those labs toward shell companies and other new workarounds. Read more: https://t.co/ozRAcPjKBs Thousands of Chinese token resellers are giving AI labs unauthorized access to Anthropic’s Claude, helping them distill U.S. models. Anthropic’s crackdown is pushing those labs toward shell companies and other new workarounds. Read more: https://t.co/ozRAcPjKBsview source ↗
-
• twitter 1w negativeThe better AI gets at writing code, 𝘁𝗵𝗲 𝗺𝗼𝗿𝗲 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝘆𝗼𝘂 𝘀𝗵𝗼𝘂𝗹𝗱 𝘄𝗿𝗶𝘁𝗲. Turn the way you want things done into ready-made functions for the agent, then use lint to block the other ways. The only option it has left is the one you want. Start with the mistakes your agent keeps making. Give each one a lint rule whos… The better AI gets at writing code, 𝘁𝗵𝗲 𝗺𝗼𝗿𝗲 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝘆𝗼𝘂 𝘀𝗵𝗼𝘂𝗹𝗱 𝘄𝗿𝗶𝘁𝗲. Turn the way you want things done into ready-made functions for the agent, then use lint to block the other ways. The only option it has left is the one you want. Start with the mistakes your agent keeps making. Give each one a lint rule whose error message names the function to use, and when the agent runs its checks, 𝗶𝘁 𝘀𝗲𝗲𝘀 𝘁𝗵𝗲 𝗲𝗿𝗿𝗼𝗿 𝗮𝗻𝗱 𝗳𝗶𝘅𝗲𝘀 𝗶𝘁 𝗼𝗻 𝗶𝘁𝘀 𝗼𝘄𝗻. Send this to Claude Code or Codex 👇 "Go through the corrections in AGENTS.md or CLAUDE.md and the last 50 commits in this repo (focus on fixes and reverts). Find patterns the agent keeps getting wrong that lint can catch, up to 3. If you find fewer, report fewer. For each one: 1. Write a helper function or type that wraps the right way to do it 2. Add a rule in the lint tool the project already uses that bans the old pattern, with an error message that names the helper to use. Prefer the tool's built-in ban rules 3. Replace the old pattern in existing code, then run lint and the tests to confirm they pass Finally, add a line to AGENTS.md or CLAUDE.md (whichever the project uses): after writing code, run lint and switch to the helper the error points to. If the project has no lint tool, tell me first. Show me the list first, with where each pattern came from and how many current violations it has. Change nothing until I confirm."view source ↗
-
• twitter 1w neutralShare of adults who use 𝕏 1. 🇯🇵 Japan: 51% 2. 🇹🇷 Türkiye: 35% 3. 🇲🇾 Malaysia: 30% 4. 🇨🇱 Chile: 30% 5. 🇰🇷 South Korea: 28% 6. 🇸🇬 Singapore: 26% 7. 🇮🇱 Israel: 26% 8. 🇳🇬 Nigeria: 26% 9. 🇪🇸 Spain: 25% 10. 🇲🇽 Mexico: 24% 11. 🇵🇪 Peru: 23% 12. 🇬🇧 United Kingdom: 22% 13. 🇦🇷 Argentina: 22% 14. 🇨🇴 Colombia: 22% 15. 🇹🇭 Thailand:… Share of adults who use 𝕏 1. 🇯🇵 Japan: 51% 2. 🇹🇷 Türkiye: 35% 3. 🇲🇾 Malaysia: 30% 4. 🇨🇱 Chile: 30% 5. 🇰🇷 South Korea: 28% 6. 🇸🇬 Singapore: 26% 7. 🇮🇱 Israel: 26% 8. 🇳🇬 Nigeria: 26% 9. 🇪🇸 Spain: 25% 10. 🇲🇽 Mexico: 24% 11. 🇵🇪 Peru: 23% 12. 🇬🇧 United Kingdom: 22% 13. 🇦🇷 Argentina: 22% 14. 🇨🇴 Colombia: 22% 15. 🇹🇭 Thailand: 20% 16. 🇦🇺 Australia: 19% 17. 🇵🇭 Philippines: 19% 18. 🇺🇸 United States: 18% 19. 🇨🇦 Canada: 18% 20. 🇵🇱 Poland: 18% 21. 🇬🇭 Ghana: 16% 22. 🇰🇪 Kenya: 16% 23. 🇮🇩 Indonesia: 15% 24. 🇵🇸 West Bank & East Jerusalem: 14% 25. 🇿🇦 South Africa: 14% 26. 🇬🇷 Greece: 13% 27. 🇸🇪 Sweden: 13% 28. 🇫🇷 France: 12% 29. 🇮🇹 Italy: 12% 30. 🇳🇱 Netherlands: 12% 31. 🇩🇪 Germany: 10% 32. 🇭🇺 Hungary: 10% 33. 🇮🇳 India: 7% 34. 🇱🇰 Sri Lanka: 7% 35. 🇧🇷 Brazil: 7% 36. 🇵🇰 Pakistan: 6% 37. 🇧🇩 Bangladesh: 2% Source: Pew Research Center, Spring 2026 Global Attitudes Surveyview source ↗
-
• twitter 1w neutralhttps://t.co/i4oI8KQLTr https://t.co/i4oI8KQLTrview source ↗
-
• twitter 1w positiveDue to abnormally high abuse, we are pausing the free DeepSeek-V4.1-Flash promotion. We are actively investigating and trying to mitigate the situation. Due to abnormally high abuse, we are pausing the free DeepSeek-V4.1-Flash promotion. We are actively investigating and trying to mitigate the situation.view source ↗
-
• twitter 1w neutralhttps://t.co/6AvOW7LVgL https://t.co/6AvOW7LVgLview source ↗
-
• twitter 1w neutralBelieve in yourself. Stay focused. Keep going. You will make it. Believe in yourself. Stay focused. Keep going. You will make it.view source ↗
-
• twitter 1w neutralFlying to SF tomorrow, which LLM do i download? Flying to SF tomorrow, which LLM do i download?view source ↗
-
• twitter 1w positivebelieve me, we are going to see some of the best from Anthropic and OpenAI before the Anthropic IPO. Fable 5.5 could be coming soon and i am genuinely excited for it. now I want to see what OpenAI comes back with. we are definitely going to benefit from this competition. believe me, we are going to see some of the best from Anthropic and OpenAI before the Anthropic IPO. Fable 5.5 could be coming soon and i am genuinely excited for it. now I want to see what OpenAI comes back with. we are definitely going to benefit from this competition.view source ↗