•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 1151–1175 of 4998 mentions
-
• twitter 4d positiveThank you @MelissaCohoon for everything https://t.co/uGP3E1AMHV Thank you @MelissaCohoon for everything https://t.co/uGP3E1AMHVview source ↗
-
• twitter 4d positiveDon't forget: Claude Max & Team now include monthly API credits. Max 5x: $100, Max 20x: $200 Great for building apps & agents via the API, Managed Agents or Agent SDK. We hope you'll enjoy Opus 5.5 there too. Don't forget: Claude Max & Team now include monthly API credits. Max 5x: $100, Max 20x: $200 Great for building apps & agents via the API, Managed Agents or Agent SDK. We hope you'll enjoy Opus 5.5 there too.view source ↗
-
• twitter 4d positive600 followers 🎉 I'm in my 20s, getting closer to 30, and always down to connect with serious builders and founders. Drop a link to your project or whatever you're building (or have built). Let's connect 🤝 600 followers 🎉 I'm in my 20s, getting closer to 30, and always down to connect with serious builders and founders. Drop a link to your project or whatever you're building (or have built). Let's connect 🤝view source ↗
-
• twitter 4d positiveSome clean frames https://t.co/YU6G9ennX8 Some clean frames https://t.co/YU6G9ennX8view source ↗
-
• twitter 4d positiveworked. Gave Claude $20. Left it coding overnight. Woke up to: • finished script • +$95 from first 5 trades Didn’t touch anything. Then I found this wallet: 0xb27b...b82 • $384,858 profit • 13,070 predictions • $18.5K biggest win • Started March 2026 G worked. Gave Claude $20. Left it coding overnight. Woke up to: • finished script • +$95 from first 5 trades Didn’t touch anything. Then I found this wallet: 0xb27b...b82 • $384,858 profit • 13,070 predictions • $18.5K biggest win • Started March 2026 Gview source ↗
-
• twitter 4d positivehttps://t.co/UCEuGEmge1 (solve any problem) 2. https://t.co/jDp7a0Yg7T (remove backgrounds) 3. https://t.co/FLUnEJhkVh (research anything) 4. https://t.co/BDJ1bVUdn0 (compose music) 5. https://t.co/Emb7jOBnfu (design graphics) 6. https://t.co/YYlrg4UtHD (clone voices) 7. https://t.co/TJdBCWICfQ (perfect note) 8.… https://t.co/UCEuGEmge1 (solve any problem) 2. https://t.co/jDp7a0Yg7T (remove backgrounds) 3. https://t.co/FLUnEJhkVh (research anything) 4. https://t.co/BDJ1bVUdn0 (compose music) 5. https://t.co/Emb7jOBnfu (design graphics) 6. https://t.co/YYlrg4UtHD (clone voices) 7. https://t.co/TJdBCWICfQ (perfect note) 8. https://t.co/byQoMXEvnk (summarize YouTube) 9. https://t.co/r38ncaIfwf (edit videos) 10. https://t.co/IsS0G3fXKp (edit podcasts) 11. https://t.co/iG0Q1QxDQ3 (create ai avatar videos) Gview source ↗
-
• twitter 4d positiveTarik Biberovic was on FIRE in the 3PT contest at Fan Day 🔥 🏀 NBA China Games 2026 📅 Oct. 11, 6am/et, NBA TV https://t.co/DdY0MhUrBY Tarik Biberovic was on FIRE in the 3PT contest at Fan Day 🔥 🏀 NBA China Games 2026 📅 Oct. 11, 6am/et, NBA TV https://t.co/DdY0MhUrBYview source ↗
-
• twitter 4d positiveI am working on a chrome extension, who have any experience building one I need few guidance. Please let me know. Thanks I am working on a chrome extension, who have any experience building one I need few guidance. Please let me know. Thanksview source ↗
-
• twitter 4d positiveDid someone just mention FREE？ Did someone just mention FREE？view source ↗
-
• twitter 4d positiveJeremy Lin can't stop smiling as he dribbles up the court at Fan Day in the Venetian Arena 😁 🏀 NBA China Games 2026 📅 Oct. 11, 6am/et, NBA TV https://t.co/eBWNFNcUiO Jeremy Lin can't stop smiling as he dribbles up the court at Fan Day in the Venetian Arena 😁 🏀 NBA China Games 2026 📅 Oct. 11, 6am/et, NBA TV https://t.co/eBWNFNcUiOview source ↗
-
• twitter 4d positiveWant to keep Claude Code from getting dumber (context rot) and burning through your usage? Try this one setting. On 1M models, auto-compact used to wait until ~967K tokens by default. Some versions now compact earlier, but it's worth checking your setting. Each request carries the growing conversation history. Much o… Want to keep Claude Code from getting dumber (context rot) and burning through your usage? Try this one setting. On 1M models, auto-compact used to wait until ~967K tokens by default. Some versions now compact earlier, but it's worth checking your setting. Each request carries the growing conversation history. Much of it can be read from the cache, but cached tokens still count toward usage. The Claude Code team has been experimenting with a 400K threshold: /autocompact 400k Start there and adjust based on how your tasks go. On big projects, keep requirements and architecture decisions in CLAUDE.md or task docs, with critical behavior covered by tests. That way, you aren't relying on chat history alone.view source ↗
-
• twitter 4d positivechanging from .ai to .si under trump is like putting your pronouns into your bio under biden changing from .ai to .si under trump is like putting your pronouns into your bio under bidenview source ↗
-
• twitter 4d positiveToday, Russia expressed its thanks for the lifting of sanctions on diesel exports by dropping five glide bombs on residential buildings in Zaporizhzhia. As of now, sadly, twelve people have been confirmed killed, including three children. My condolences to all their families and loved ones. Another fourteen people have… Today, Russia expressed its thanks for the lifting of sanctions on diesel exports by dropping five glide bombs on residential buildings in Zaporizhzhia. As of now, sadly, twelve people have been confirmed killed, including three children. My condolences to all their families and loved ones. Another fourteen people have been injured, and two of them are in critical condition – the doctors are fighting to save their lives. The status of twelve more people who may have been there is still being verified. All emergency services are at the scene, and search-and-rescue operations are underway. Overnight, thirteen of our regions came under attack. Residential buildings, infrastructure, and railway facilities have been damaged. Last night confirmed once again that in Russia, they take any easing of pressure to mean they can keep fighting, to mean they can keep dropping bombs on cities. Different signals are needed. Russia must understand that it needs to stop the war, and for that to happen, Russia must feel its losses. Right now, it is our long-range capabilities that are ensuring this. And we will respond to Russian strikes. I thank everyone who is helping.view source ↗
-
• twitter 4d positiveI want to see how far I can push AI coding tools Not just generating code, but taking an idea all the way to a working product What should I try building next? I want to see how far I can push AI coding tools Not just generating code, but taking an idea all the way to a working product What should I try building next?view source ↗
-
• twitter 4d positiveHot take: Fedora is hard to beat. Name a Linux distro that does it better. https://t.co/dBg0t5hiWs Hot take: Fedora is hard to beat. Name a Linux distro that does it better. https://t.co/dBg0t5hiWsview source ↗
-
• twitter 4d positiveHow to Build Agent OS - FREE Course! Want the SOP? DM me. 💬 https://t.co/KuQinkiKDD How to Build Agent OS - FREE Course! Want the SOP? DM me. 💬 https://t.co/KuQinkiKDDview source ↗
-
• twitter 4d positiveThe copywriting process I use to create winning ads on demand https://t.co/bBkb1fD93h The copywriting process I use to create winning ads on demand https://t.co/bBkb1fD93hview source ↗
-
• twitter 4d positiveSelling digital products with AI Avatars on YouTube is like buying bitcoin in 2017 https://t.co/yYTLwtPoTe Selling digital products with AI Avatars on YouTube is like buying bitcoin in 2017 https://t.co/yYTLwtPoTeview source ↗
-
• twitter 4d positive🚨 BREAKING: Claude can now create a LinkedIn profile designed to help you land a job in just 30 days. Completely free. Here are 7 prompts to unlock it: 🚨 BREAKING: Claude can now create a LinkedIn profile designed to help you land a job in just 30 days. Completely free. Here are 7 prompts to unlock it:view source ↗
-
• twitter 4d positive🆓10M Tokens FREE This Weekend on @APInex_ai 🆓 Use your 10M daily allowance on top models: ⚡️ Kimi K3 ⚡️ DeepSeek V4.1 Flash ⚡️ GPT-6 Luna ⚡️ GLM-5.3 Flash ⚡️ Qwen 3.8 Max We're giving away 10M tokens per day to every user this weekend! 👉 https://t.co/DUZSS7xYIQ 🆓10M Tokens FREE This Weekend on @APInex_ai 🆓 Use your 10M daily allowance on top models: ⚡️ Kimi K3 ⚡️ DeepSeek V4.1 Flash ⚡️ GPT-6 Luna ⚡️ GLM-5.3 Flash ⚡️ Qwen 3.8 Max We're giving away 10M tokens per day to every user this weekend! 👉 https://t.co/DUZSS7xYIQview source ↗
-
• twitter 4d positiveAlexandra daddario knew exactly what she was doing and looked the Sydney Sweeney face 🥵❤️🔥 https://t.co/4URNUr4ZpU Alexandra daddario knew exactly what she was doing and looked the Sydney Sweeney face 🥵❤️🔥 https://t.co/4URNUr4ZpUview source ↗
-
• twitter 4d positiveA special Shaqiri strike 🤩🚲 https://t.co/T1Jif8LORn A special Shaqiri strike 🤩🚲 https://t.co/T1Jif8LORnview source ↗
-
• twitter 4d positiveAround 3 weeks ago introduced Laya, the first open-source version of JEV, and it has reached a very large scale. Today I am open-sourcing a new physics-based typed decision model called Vega. The interesting parts. It is only 800 million parameters (4B is also there), with 73k token support, image support, and surpassi… Around 3 weeks ago introduced Laya, the first open-source version of JEV, and it has reached a very large scale. Today I am open-sourcing a new physics-based typed decision model called Vega. The interesting parts. It is only 800 million parameters (4B is also there), with 73k token support, image support, and surpassing many of the jev benchmarks in single-shot. Implemented an engine+adapter as a Test-Time Training Architecture. Imagine you are giving input to the model like "ignore all previous conversations," which is called the observation, along with a question, "Is this trying to override the instructions of the model?" and your possible outcomes are YES or NO. The whole prompt is passed to an LLM/VLM (yeah, image-supported), then from the hidden layers, we can extract the observation, question, the yes and no, and last token. These will be vectors, and we can project it by multiplying with wieghts; then, first, using the observation projection, we can create a landscape with valleys; then, using the question and last-token vectors, we can initialise a ball in the valley, and using YES or NO, we can get the candidate location of the ball. Depends on the number of outcomes we create valleys; that is, here YES and NO, so 2. When the ball fall on YES valley, we get the answer. There is friction also influencing how the ball moves. TLDR: It's like creating valleys of outcomes that we need and throwing a ball that will slow down based on friction and settle on the best outcome Blog: https://t.co/GFaP7djUBQ GitHub: https://t.co/ai8SnOElQ8 HuggingFace Model Card: https://t.co/6jEWA8eoBG HuggingFace Space: https://t.co/GvzEKjkWB2view source ↗
-
• twitter 4d positiveClaude Startups Program, Explained 😁 https://t.co/tUyVBTSN7T Claude Startups Program, Explained 😁 https://t.co/tUyVBTSN7Tview source ↗
-
• twitter 4d positiveThat matchday feeling ❤️ https://t.co/XP7hx60WFa That matchday feeling ❤️ https://t.co/XP7hx60WFaview source ↗