•twitter5200
listening to
timeline
5200
mentions
tracked
tracked
net sentiment
+24%
1633 positive
3179 neutral
388 negative
volume & sentiment over time
Sep 30 – Oct 5, 2026 · Daily
sources
most discussed
—
active days
6
mentions
Showing 376–400 of 1633 mentions
-
• twitter 19h positiveFor folks who Grok @bot: 1. How many bots do you all have? 2. What are your top 3 most used bots? Let us know in the replies! I thought I was cool with my 8-9 bots but talking to some @SpaceXAI employees they have 50+ bots (!) and use a few manager bots to orchestrate all of them. For folks who Grok @bot: 1. How many bots do you all have? 2. What are your top 3 most used bots? Let us know in the replies! I thought I was cool with my 8-9 bots but talking to some @SpaceXAI employees they have 50+ bots (!) and use a few manager bots to orchestrate all of them.view source ↗
-
• twitter 19h positiveYoung men, The WIN is coming. Don't let the WHEN worry you. Young men, The WIN is coming. Don't let the WHEN worry you.view source ↗
-
• twitter 19h positiveThis AI agent costs basically NOTHING to think. 🤯 Hermes is free. The AI models can be free too. Run it in the cloud 24/7 while you sleep. If one brain taps out… just swap in another. 😂 Your AI employee just discovered unlimited coffee. Link in the comments 👇 https://t.co/OEJ7oPZAEe This AI agent costs basically NOTHING to think. 🤯 Hermes is free. The AI models can be free too. Run it in the cloud 24/7 while you sleep. If one brain taps out… just swap in another. 😂 Your AI employee just discovered unlimited coffee. Link in the comments 👇 https://t.co/OEJ7oPZAEeview source ↗
-
• twitter 20h positiveNever call a bro lazy just because it's your winning season. Never call a bro lazy just because it's your winning season.view source ↗
-
• twitter 20h positiveClaude Coders: Opus 5.5 Ultracode just got way better '/effort' 1. Set model to Opus 5.5 2. Press Tab to turn Ultracode on Claude will write an orchestration script for each big task, then send a swarm of subagents to run it set it once per model and forget it: https://t.co/9W4NLIe0kI Claude Coders: Opus 5.5 Ultracode just got way better '/effort' 1. Set model to Opus 5.5 2. Press Tab to turn Ultracode on Claude will write an orchestration script for each big task, then send a swarm of subagents to run it set it once per model and forget it: https://t.co/9W4NLIe0kIview source ↗
-
• twitter 20h positiveOpenNOW😱😮😱😱😱😱😍😍😍 https://t.co/RIA9n9uOMY https://t.co/pBrFqHNRDi OpenNOW😱😮😱😱😱😱😍😍😍 https://t.co/RIA9n9uOMY https://t.co/pBrFqHNRDiview source ↗
-
• twitter 20h positiveclaude code MODS might be the best thing to happen to claude code since claude code itself.... genuinely f**king shocked why more people aren’t building their own. you can ask it to swap in your won features, change how it behaves and customise ui here's everything you need to master building mods: claude code MODS might be the best thing to happen to claude code since claude code itself.... genuinely f**king shocked why more people aren’t building their own. you can ask it to swap in your won features, change how it behaves and customise ui here's everything you need to master building mods:view source ↗
-
• twitter 20h positiveThank you for assembling to make Avengers: Endgame the biggest movie of all time. We love you 3000. https://t.co/eZFbN1x724 Thank you for assembling to make Avengers: Endgame the biggest movie of all time. We love you 3000. https://t.co/eZFbN1x724view source ↗
-
• twitter 20h positiveMy ChatGPT Pro sub ends tomorrow. I'm not renewing it. Opus 5.5 is the better model, and the limits are better too. Astra was good, but I had to babysit it. Tibo resets help. But, that's not a reason to stay. Which subscription are you on? My ChatGPT Pro sub ends tomorrow. I'm not renewing it. Opus 5.5 is the better model, and the limits are better too. Astra was good, but I had to babysit it. Tibo resets help. But, that's not a reason to stay. Which subscription are you on?view source ↗
-
• twitter 20h positiveOR get a $10/month VPS install coolify/dokploy to manage everything one server can handle all of your projects run whatever database you like on it AI is so good now that you don’t need stuff like supabase/firebase anymore OR get a $10/month VPS install coolify/dokploy to manage everything one server can handle all of your projects run whatever database you like on it AI is so good now that you don’t need stuff like supabase/firebase anymoreview source ↗
-
• twitter 20h positiveIn the long run, the right opportunities don't just find you, they recognize you. Sometimes you work so hard toward something only to watch it go to someone else. It feels like losing something that was already yours. But keep working. Keep building. Keep becoming someone the right things are drawn to. What's yours … In the long run, the right opportunities don't just find you, they recognize you. Sometimes you work so hard toward something only to watch it go to someone else. It feels like losing something that was already yours. But keep working. Keep building. Keep becoming someone the right things are drawn to. What's yours will find you. It always does.view source ↗
-
• twitter 20h positiveAndrej Karpathy built an agent that runs AI research autonomously. The whole setup is just 3 files It's called autoresearch. You give Claude or Codex a small LLM training setup and walk away. The loop: > try one idea in https://t.co/293zgMo6Bh > commit > train for exactly 5 minutes > if score improved - keep it. Wor… Andrej Karpathy built an agent that runs AI research autonomously. The whole setup is just 3 files It's called autoresearch. You give Claude or Codex a small LLM training setup and walk away. The loop: > try one idea in https://t.co/293zgMo6Bh > commit > train for exactly 5 minutes > if score improved - keep it. Worse - git reset > log the result, repeat forever The instructions literally tell the agent to never stop and never ask "should I keep going?", because the human might be asleep. You don't touch the Python at all. You only edit program.md, the agent's instructions. Karpathy calls it the code of your research org. There's even a simplicity rule. A tiny gain that adds 20 lines of hacky code gets thrown out. Same score with less code gets kept. I think this pattern works way beyond LLMs. Anything with one number to beat, one file to edit and a fixed time per run can grind overnight like this. 92k stars, MIT. Runs on one NVIDIA GPU, local or rented, with community forks for Mac, Windows and AMD. repo: https://t.co/79UWtuLyk1view source ↗
-
• twitter 20h positiveI live in Kazakhstan Most of my clients are in the US That's a 12 hour difference But I'm always in touch with them Need edits, a call or just to talk through the project? The time zone never gets in the way I like this work too much https://t.co/issMMMv0bl I live in Kazakhstan Most of my clients are in the US That's a 12 hour difference But I'm always in touch with them Need edits, a call or just to talk through the project? The time zone never gets in the way I like this work too much https://t.co/issMMMv0blview source ↗
-
• twitter 20h positiveHermes BotScreen gives your AI its own desktop to work on. Keep using your screen while your agent handles its task. Here’s what the setup shown in this video includes: → A separate Linux desktop for the agent. → Its own browser, mouse, keyboard, and terminal. → A live view so you can watch it work. → Browser ses… Hermes BotScreen gives your AI its own desktop to work on. Keep using your screen while your agent handles its task. Here’s what the setup shown in this video includes: → A separate Linux desktop for the agent. → Its own browser, mouse, keyboard, and terminal. → A live view so you can watch it work. → Browser sessions with saved logins. → Scheduled tasks for repeat jobs. → Controls to check, start, and stop the instance. You give Hermes an instruction, then inspect what happens on its screen. Start with a simple website visit and summary. Save this video, you’ll know what an agent with its own desktop looks like. Want the SOP? DM me. 💬view source ↗
-
• twitter 20h positiveAn awesome nickname: “the Baklava Bomber”. An awesome nickname: “the Baklava Bomber”.view source ↗
-
• twitter 20h positiveGive it time. Some blessings are worth waiting a little longer for. Give it time. Some blessings are worth waiting a little longer for.view source ↗
-
• twitter 20h positive🚨 Codex Users!! GPT-6 Astra Light is WAY too good for Codex Plus users If you’re on Plus and want to use Astra, we’ve been testing it for almost 1 hour 30 minutes… And the 5-hour window is honestly insane 20% of the 5-hour window still available after that much testing The limit almost doesn’t even feel real 🚨 Codex Users!! GPT-6 Astra Light is WAY too good for Codex Plus users If you’re on Plus and want to use Astra, we’ve been testing it for almost 1 hour 30 minutes… And the 5-hour window is honestly insane 20% of the 5-hour window still available after that much testing The limit almost doesn’t even feel realview source ↗
-
• twitter 20h positiveYour startup doesn’t need to be perfect when customers are already happily paying you. Your startup doesn’t need to be perfect when customers are already happily paying you.view source ↗
-
• twitter 20h positiveis this good as an ad? https://t.co/9N6qAjgzfP is this good as an ad? https://t.co/9N6qAjgzfPview source ↗
-
• twitter 20h positiveIt's crazy to think that a week ago nobody was reading my posts. I've only met nice people on X. I love you all 🙌🏻 🫶🏻 https://t.co/NvfQupJ4w6 It's crazy to think that a week ago nobody was reading my posts. I've only met nice people on X. I love you all 🙌🏻 🫶🏻 https://t.co/NvfQupJ4w6view source ↗
-
• twitter 20h positiveHOLY SH*T… Perplexity AI can clock in forever. 🤯 Give it ONE job and it keeps doing it. It can watch emails, leads, Slack, and more. Best part? It remembers what happened last time. My AI now has better attendance than most humans. 😂 Link in the comments 👇 https://t.co/u1iIqw0xUM HOLY SH*T… Perplexity AI can clock in forever. 🤯 Give it ONE job and it keeps doing it. It can watch emails, leads, Slack, and more. Best part? It remembers what happened last time. My AI now has better attendance than most humans. 😂 Link in the comments 👇 https://t.co/u1iIqw0xUMview source ↗
-
• twitter 20h positiveThank you to our wonderful sponsors @WorkOS and @DeveloperXM for supporting the podcast: 🏆 @WorkOS — Make your app Enterprise Ready, with SSO, SCIM, RBAC, and more: https://t.co/XH3bKmeEkH 🏆 @DeveloperXM—Engineering intelligence for the AI era: https://t.co/xQczIxacrc Also available on: • Spotify: https://t.co/uLGRliQ… Thank you to our wonderful sponsors @WorkOS and @DeveloperXM for supporting the podcast: 🏆 @WorkOS — Make your app Enterprise Ready, with SSO, SCIM, RBAC, and more: https://t.co/XH3bKmeEkH 🏆 @DeveloperXM—Engineering intelligence for the AI era: https://t.co/xQczIxacrc Also available on: • Spotify: https://t.co/uLGRliQyHs • Apple: https://t.co/LnWokqsnmWview source ↗
-
• twitter 20h positiveWhy do you have to be vertically integrated to be a data center provider today? “The supply chain to support large-scale AI data centers is sort of like a game of Whac-A-Mole. At different points, different bottlenecks come into play. One of the key bottlenecks was a power distribution center. The lead time for this … Why do you have to be vertically integrated to be a data center provider today? “The supply chain to support large-scale AI data centers is sort of like a game of Whac-A-Mole. At different points, different bottlenecks come into play. One of the key bottlenecks was a power distribution center. The lead time for this one component was 100 weeks, and I said, ‘Well, I do not have 100 weeks.’ We had consciously vertically integrated electrical manufacturing. We were able to do it in 28 weeks, and having the resources internally gives you a lot more flexibility to unblock these key bottlenecks.” @ChaseLochmiller Love to hear your thoughts @stephenbalaban @MattLoszak @BrianGittview source ↗
-
• twitter 20h positiveHere's my best videos in 2026 🚀 (the beat synced goes so hard 🤯!!) https://t.co/UUirlSzrFZ Here's my best videos in 2026 🚀 (the beat synced goes so hard 🤯!!) https://t.co/UUirlSzrFZview source ↗
-
• twitter 20h positiveRT @brivael: Grok is now making all boring stuff for me. For Argil. For personal stuff. It’s like having a 10-person S-tier team working… RT @brivael: Grok is now making all boring stuff for me. For Argil. For personal stuff. It’s like having a 10-person S-tier team working…view source ↗