•twitter5981
listening to
timeline
5981
mentions
tracked
tracked
net sentiment
+24%
1895 positive
3629 neutral
457 negative
volume & sentiment over time
Sep 30 – Oct 5, 2026 · Daily
sources
most discussed
—
active days
6
mentions
Showing 1176–1200 of 5981 mentions
-
• twitter 19h neutralOf course I had it just build the hot reloading jvm runtime and custom mod launcher from scratch. It's just for me, only had to work on Linux and on my own tailscale network. Idc about anyone else. I want my kids to have fun and be creative! Of course I had it just build the hot reloading jvm runtime and custom mod launcher from scratch. It's just for me, only had to work on Linux and on my own tailscale network. Idc about anyone else. I want my kids to have fun and be creative!view source ↗
-
• twitter 19h positiveReputation is one of the most valuable assets you’ll ever own, it’s built through: ✔️ Consistency in your actions ✔️ Integrity in your choices ✔️ Trust in your relationships But it can be destroyed in an instant, through one careless word, one unethical decision, or one moment of short-term thinking. In leadership, b… Reputation is one of the most valuable assets you’ll ever own, it’s built through: ✔️ Consistency in your actions ✔️ Integrity in your choices ✔️ Trust in your relationships But it can be destroyed in an instant, through one careless word, one unethical decision, or one moment of short-term thinking. In leadership, business, and life, people don’t just remember what you achieved, they remember how you achieved it.view source ↗
-
• twitter 19h neutralIn a year when both the rupee and the stock market skidded, down 8.5% and 9.5%, respectively, India’s richest tycoons showed resilience. Their collective wealth of $1 trillion is unchanged from when fortunes were last measured. See the list of their 100 wealthiest residents: https://t.co/CcMW5MMj4K 📸: Getty Images In a year when both the rupee and the stock market skidded, down 8.5% and 9.5%, respectively, India’s richest tycoons showed resilience. Their collective wealth of $1 trillion is unchanged from when fortunes were last measured. See the list of their 100 wealthiest residents: https://t.co/CcMW5MMj4K 📸: Getty Imagesview source ↗
-
• twitter 19h neutral🐍📺 Deploy Your Python Script on the Web With Flask [Video] #python https://t.co/tBDZ9Aonwf 🐍📺 Deploy Your Python Script on the Web With Flask [Video] #python https://t.co/tBDZ9Aonwfview source ↗
-
• twitter 19h positiveGreat overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from UT Austin on context compression in coding agents. They ran nearly 35,000 agent runs on SWE-bench Verified and Termi… Great overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from UT Austin on context compression in coding agents. They ran nearly 35,000 agent runs on SWE-bench Verified and Terminal-Bench and varied three decisions separately. These are how context is compressed, when compression triggers, and how much is removed. On Terminal-Bench with Qwen, policies that use about a third of the tokens can take 20% to 80% longer than keeping full context. Step-triggered policies cut the most tokens per step but need 10% to 27% more model calls. Threshold-triggered policies cut tokens by 22% to 55% with call counts close to full context. Results also differ by model. A policy that works well for Qwen drops Devstral to 38.7% and makes it slower, so measure latency and cost per model before choosing one. Paper: https://t.co/1v9eR7DLAn Chat with Paper: https://t.co/tGi6A2YIU8view source ↗
-
• twitter 19h negative98% of people aren't paying for an AI subscription. Less than 0.5% are using an AI agent. You NEED to set one of these up ASAP: • Muse • Grok Bot • Hermes • Dots • Cue (by Manus) • Openclaw? The most expensive mistake you could make is not using these. 98% of people aren't paying for an AI subscription. Less than 0.5% are using an AI agent. You NEED to set one of these up ASAP: • Muse • Grok Bot • Hermes • Dots • Cue (by Manus) • Openclaw? The most expensive mistake you could make is not using these.view source ↗
-
• twitter 19h negativeTurn one coaching call into a full week of content. Give Ling 3.1 Flash the transcript. It pulls out every question and answer, finds missing tutorial ideas, and writes 5 community posts. One call. Five posts. Less work. Want the SOP? DM me. https://t.co/3z48xohBxM Turn one coaching call into a full week of content. Give Ling 3.1 Flash the transcript. It pulls out every question and answer, finds missing tutorial ideas, and writes 5 community posts. One call. Five posts. Less work. Want the SOP? DM me. https://t.co/3z48xohBxMview source ↗
-
• twitter 19h negativeEvery vibe coder's security prompt: "My vibe-coded app just leaked user data. - Move every API key to env variables. - Rotate the keys I already pushed to GitHub. - Add .env to .gitignore. - Turn on row-level security in Supabase. - Never trust the client, validate on the server. - Add auth checks to every API route. … Every vibe coder's security prompt: "My vibe-coded app just leaked user data. - Move every API key to env variables. - Rotate the keys I already pushed to GitHub. - Add .env to .gitignore. - Turn on row-level security in Supabase. - Never trust the client, validate on the server. - Add auth checks to every API route. - Rate-limit login and signup. - Hash passwords, never store them raw. - Use HTTPS everywhere. - Set CORS to my domain only. - Sanitize every input against SQL injection. - Escape output to block XSS. - Add CSRF protection to forms. - Lock down file uploads by type and size. - Hide stack traces in production. - Set secure, httpOnly cookies. - Update every outdated package. - Log every failed login. - Back up the database daily. - Add a spending cap on my AI API keys. Make it unhackable by Friday. Make no mistakes." Funny thing is, this is actually the whole security checklist. Bookmark it. Paste it into Claude Code. Then actually check the last two yourself.view source ↗
-
• twitter 19h neutralशुचित्वं त्यागिता शौर्यं सामान्यं सुखदुःखयोः। दाक्षिण्यं चानुरक्तिश्च सत्यता च सुहृद्गुणाः॥ https://t.co/vKvqfnXsCm शुचित्वं त्यागिता शौर्यं सामान्यं सुखदुःखयोः। दाक्षिण्यं चानुरक्तिश्च सत्यता च सुहृद्गुणाः॥ https://t.co/vKvqfnXsCmview source ↗
-
• twitter 19h positiveHave been playing bedrock with my kids for a bit for Minecraft, but it occurred to me you can do so many insane things with java edition... It doesn't have controller support on Linux ootb? Cool, I'll add it. Just one prompt. Syncing mods across tailscale, cool one prompt. Custom UI that doesn't suck for controllers, … Have been playing bedrock with my kids for a bit for Minecraft, but it occurred to me you can do so many insane things with java edition... It doesn't have controller support on Linux ootb? Cool, I'll add it. Just one prompt. Syncing mods across tailscale, cool one prompt. Custom UI that doesn't suck for controllers, ok that's a lot of prompts but possible. MAKING A TANK THAT SHOOTS TNT AFTER MY SON ASKS FOR IT, priceless (ok well I do know the token cost but you know what I mean) So hilarious, made winged pink unicorn with purple horn. So sick. My daughter was freaking out. Gonna build quests and a bunch of stuff. So funnyview source ↗
-
• twitter 19h positiveStop rebuilding slide tooling every time an agent makes a deck open-slide is a React slide framework for builders using coding agents to create presentation decks. It helps you turn a natural-language deck request into a working presentation by giving agents scaffolded authoring skills while the framework handles the… Stop rebuilding slide tooling every time an agent makes a deck open-slide is a React slide framework for builders using coding agents to create presentation decks. It helps you turn a natural-language deck request into a working presentation by giving agents scaffolded authoring skills while the framework handles the canvas, scaling, navigation, hot reload, and present mode. Key features: • Agent-native authoring – scaffolds `/create-slide` and `/slide-authoring` skills to help agents plan and write deck pages • Fixed slide canvas – renders every slide on a 1920 × 1080 canvas while pages remain arbitrary React components • In-browser feedback loop – click an element, leave a comment, then use `/apply-comments` to apply pending edits • Asset workflow – manage images, videos, and fonts per deck, with integrated svgl logo search • Presentation and export options – includes fullscreen and presenter modes, plus static HTML, PDF, and PPTX exports It’s open-source (MIT license). Link in the reply 👇view source ↗
-
• twitter 19h positiveI was brainstorming with Claude to find a name for a product and it recommended Hark. I rejected it because it sounded too harsh. Wonder if it’s the same product 👀 I was brainstorming with Claude to find a name for a product and it recommended Hark. I rejected it because it sounded too harsh. Wonder if it’s the same product 👀view source ↗
-
• twitter 19h neutralomfg, what are these numbers !!! https://t.co/etWACSS6aR omfg, what are these numbers !!! https://t.co/etWACSS6aRview source ↗
-
• twitter 19h positiveWe urgently need to speak with someone senior at @ElevenLabs regarding a serious security concern. One company account appears to have been accessed by unauthorized users, resulting in approximately $39,000 in abnormal usage within 7–14 days, versus a normal spend of only $100–$200/month. We reported this weeks ago … We urgently need to speak with someone senior at @ElevenLabs regarding a serious security concern. One company account appears to have been accessed by unauthorized users, resulting in approximately $39,000 in abnormal usage within 7–14 days, versus a normal spend of only $100–$200/month. We reported this weeks ago but still haven’t received a proper investigation. More concerning: something similar happened this week on our main company's ElevenLabs account. Fortunately, our finance team detected it within an hour. Two separate incidents (complete different companies) raise legitimate questions around account security and access. If anyone in my network can connect me with an @ElevenLabs account manager, someone from their Security / Trust & Safety team, I’d really appreciate an introduction. We can share the full timeline and evidence privately.view source ↗
-
• twitter 19h positiveRumors I've been hearing: Bel from OpenAI is an extremely good model, a lot better than Fable 5.5, and it'll probably release by the end of the year, likely December. But that doesn't mean Anthropic is going to lose. I've also heard Anthropic has done a really, really big new pretrain within the last week. This is goin… Rumors I've been hearing: Bel from OpenAI is an extremely good model, a lot better than Fable 5.5, and it'll probably release by the end of the year, likely December. But that doesn't mean Anthropic is going to lose. I've also heard Anthropic has done a really, really big new pretrain within the last week. This is going to be fun 👀view source ↗
-
• twitter 19h neutral🚨 MAYBE FIRST TIME IN CRICKET HISTORY 🚨 Ali Khan bowls a bouncer, and the ball goes for a SIX 😳 That's a Wide + Six, possibly the first time this has happened in cricket history 😂 A must watch 👇🏻 https://t.co/6QACwUgT2T 🚨 MAYBE FIRST TIME IN CRICKET HISTORY 🚨 Ali Khan bowls a bouncer, and the ball goes for a SIX 😳 That's a Wide + Six, possibly the first time this has happened in cricket history 😂 A must watch 👇🏻 https://t.co/6QACwUgT2Tview source ↗
-
• twitter 19h neutralevery founder i know struggles with distribution has anyone actually figured this shit out? every founder i know struggles with distribution has anyone actually figured this shit out?view source ↗
-
• twitter 19h positiveI took Karpathy's advice and finally tried using Opus 5.5 to create a few bespoke explainer videos (using ElevenLabs for voice). Trying different libraries for the video generation too (Remotion, Hyperframes, Manim). I'm impressed thus far. Here's some of what Opus 5.5 one-shotted (more in thread): I took Karpathy's advice and finally tried using Opus 5.5 to create a few bespoke explainer videos (using ElevenLabs for voice). Trying different libraries for the video generation too (Remotion, Hyperframes, Manim). I'm impressed thus far. Here's some of what Opus 5.5 one-shotted (more in thread):view source ↗
-
• twitter 19h neutralUS removes B-1 bombers from UK base amid security concerns https://t.co/IfwZb09e5f https://t.co/IfwZb09e5f US removes B-1 bombers from UK base amid security concerns https://t.co/IfwZb09e5f https://t.co/IfwZb09e5fview source ↗
-
• twitter 19h positiveRT @webdevMason: I don't care if I sound like a shill, my Tesla is amazing Every drive is just, wow, the car is driving Soon drunk drivin… RT @webdevMason: I don't care if I sound like a shill, my Tesla is amazing Every drive is just, wow, the car is driving Soon drunk drivin…view source ↗
-
• twitter 19h neutralYOU CAN JUST DO THINGS YOU CAN JUST DO THINGSview source ↗
-
• twitter 19h neutralAn app we helped raise $250k two months ago just raised $1M from VCs 😳 An app we helped raise $250k two months ago just raised $1M from VCs 😳view source ↗
-
• twitter 19h neutralKEATON WAGLER IN THE CLUTCH. He puts the Clippers ahead by 1 with 12.8 to go 🍿 Watch the final seconds on NBA League Pass. https://t.co/1V3ybJuL0e KEATON WAGLER IN THE CLUTCH. He puts the Clippers ahead by 1 with 12.8 to go 🍿 Watch the final seconds on NBA League Pass. https://t.co/1V3ybJuL0eview source ↗
-
• twitter 19h positiveThings my bots did this week with the built in browser: - scrape Facebook & Instagram (shhh) - build workflows in HighLevel (no MCP for this yet) - tons of QA testing for web apps and websites - create financial reports with data that isn’t API available - visually review dashboards for my portfolio companies - put … Things my bots did this week with the built in browser: - scrape Facebook & Instagram (shhh) - build workflows in HighLevel (no MCP for this yet) - tons of QA testing for web apps and websites - create financial reports with data that isn’t API available - visually review dashboards for my portfolio companies - put research and data sources in front of my face instead of just sending it in chat - other things I don’t remember local agent browser use is amazing, and now Codex isn’t the only player at bat for native browser control.view source ↗
-
• twitter 19h neutralhttps://t.co/RMlNVu3t65 https://t.co/RMlNVu3t65view source ↗