•twitter18807
listening to
timeline
18807
mentions
tracked
tracked
net sentiment
+23%
5808 positive
11597 neutral
1402 negative
volume & sentiment over time
Sep 30 – Oct 17, 2026 · Daily
sources
most discussed
—
active days
18
mentions
Showing 11701–11725 of 18807 mentions
-
• twitter 1w neutralYou're coding for the next 5 years. Which editor are you choosing? (A) VS Code (B) Cursor (C) Zed (D) Neovim You're coding for the next 5 years. Which editor are you choosing? (A) VS Code (B) Cursor (C) Zed (D) Neovimview source ↗
-
• twitter 1w neutralhttps://t.co/k3t5k5YRg2 https://t.co/k3t5k5YRg2view source ↗
-
• twitter 1w positiveAI in 2024: write my email AI in 2026: is Claude conscious? we moved fast AI in 2024: write my email AI in 2026: is Claude conscious? we moved fastview source ↗
-
• twitter 1w neutral@Teknium @alexhvnsen That was quick @Teknium @alexhvnsen That was quickview source ↗
-
• twitter 1w neutral@alexhvnsen @NousResearch Made computer use pluggable to swap out TryCUA when you're ready to get this thing on the plugins catalog 😉😉 https://t.co/s2ls0MyySQ https://t.co/kExtu3Perc @alexhvnsen @NousResearch Made computer use pluggable to swap out TryCUA when you're ready to get this thing on the plugins catalog 😉😉 https://t.co/s2ls0MyySQ https://t.co/kExtu3Percview source ↗
-
• twitter 1w neutralhey Singapore 🇸🇬 gonna meet with all ct legends today, running a bit late to the party who else is arriving today? https://t.co/jtW97bH3rP hey Singapore 🇸🇬 gonna meet with all ct legends today, running a bit late to the party who else is arriving today? https://t.co/jtW97bH3rPview source ↗
-
• twitter 1w neutral@mattzcarey Completely agree. I decided I didn't want to compete in the agents arena, so I went to the services side. @mattzcarey Completely agree. I decided I didn't want to compete in the agents arena, so I went to the services side.view source ↗
-
• twitter 1w neutralhttps://t.co/uxs0YzWbTh ⚡ FLASH SALE: $49/mo (normally $69) — only 5 spots, 60 mins left 👉 https://t.co/pketIk0u0f https://t.co/uxs0YzWbTh ⚡ FLASH SALE: $49/mo (normally $69) — only 5 spots, 60 mins left 👉 https://t.co/pketIk0u0fview source ↗
-
• twitter 1w neutralaccess: https://t.co/cbQcWqHpU0 access: https://t.co/cbQcWqHpU0view source ↗
-
• twitter 1w positiveI was the other guy in question here Turns out I’m South Indian and I don’t speak Hindi. How would you have liked it if I expected you to speak Tamil and then tweeted about it after I was the other guy in question here Turns out I’m South Indian and I don’t speak Hindi. How would you have liked it if I expected you to speak Tamil and then tweeted about it afterview source ↗
-
• twitter 1w neutralIf it’s true… Bro switched from NVIDIA to Infosys. Downfall pro max. https://t.co/Kor7mqn315 If it’s true… Bro switched from NVIDIA to Infosys. Downfall pro max. https://t.co/Kor7mqn315view source ↗
-
• twitter 1w neutralAgent Deck is a terminal dashboard that shows all your running AI coding sessions at once, so juggling work across ten projects takes one keystroke instead of ten terminals. Explore it here: https://t.co/gUOOanq6XH https://t.co/BEyz4bOY7j Agent Deck is a terminal dashboard that shows all your running AI coding sessions at once, so juggling work across ten projects takes one keystroke instead of ten terminals. Explore it here: https://t.co/gUOOanq6XH https://t.co/BEyz4bOY7jview source ↗
-
• twitter 1w neutralhttps://t.co/QFT6Ai0MT2 https://t.co/QFT6Ai0MT2view source ↗
-
• twitter 1w neutralOne way to do this is by just giving your agent tools it can use rather than text of instructions it must religiously follow. https://t.co/4vW5axoFud helps with this. One way to do this is by just giving your agent tools it can use rather than text of instructions it must religiously follow. https://t.co/4vW5axoFud helps with this.view source ↗
-
• twitter 1w negativeBuilder Arc - Learning's sharing time (Day 2) I launched lafda dot fun on Oct 4 at 12:45 PM IST, and it's been roughly 43 hours. > 20.2k pageviews, > 7.1k sessions, > 6.1k unique visitors, > average session duration 2 min 40 sec, > 94% of traffic from India, 64% on mobile, > 120 sign-ups, > 11 Lafda submissions, > 0 … Builder Arc - Learning's sharing time (Day 2) I launched lafda dot fun on Oct 4 at 12:45 PM IST, and it's been roughly 43 hours. > 20.2k pageviews, > 7.1k sessions, > 6.1k unique visitors, > average session duration 2 min 40 sec, > 94% of traffic from India, 64% on mobile, > 120 sign-ups, > 11 Lafda submissions, > 0 premium users so far (excluding me, of course). Now let's talk about bugs and glitches. I shipped 8 PRs since the last post, and 4 of them were fixes. From logging and observability, I caught: > One backend error was 97% of all my errors. Signed-out readers on a post page hit an account endpoint, got "not signed in" 3,867 times, and some saw a "Sign in required" toast without clicking anything. Fixed. It dropped from 3,738 a day to 2. > Every backend error was logged twice. Now it's logged once. (i forgot to turn of STDIO it in prod) > Failed sign-ins left no trace in my logs. Now they do. > Hydration error on the post page for signed-in readers (the page rendered twice). Fixed. > I removed my auth rate limit. Behind Cloudflare, many users shared one IP bucket, so real users could get blocked. Instead moved rate limit to WAF. > Big pastes failed to save (over 400 edits at once). Fixed. Only 1 user hit it (me ofc) From user reporting: > None Also shipped: notifications for comments and upvotes, a better paywall, an About page, and writing guidelines & enabled web vitals. I will report back with the analytics, issues, and monetization details.view source ↗
-
• twitter 1w positiveTurning a useful agent prompt into a repeatable workflow shouldn’t start from a blank page. https://t.co/nTJb9JCPnj is a community-maintained directory of ready-to-use agent prompts for Grok Bot, Rakazo, and other agents. It helps you find and reuse scheduled-bot setups by making prompts copy-pasteable for work like … Turning a useful agent prompt into a repeatable workflow shouldn’t start from a blank page. https://t.co/nTJb9JCPnj is a community-maintained directory of ready-to-use agent prompts for Grok Bot, Rakazo, and other agents. It helps you find and reuse scheduled-bot setups by making prompts copy-pasteable for work like email triage, daily briefings, SEO fixes, and churn warnings. Key features: • Ready-to-use prompts – copy a prompt into your agent to set up a scheduled bot • Practical workflow examples – listings cover email triage, daily briefings, SEO fixes, and churn warnings • Markdown-based contributions – add one file in `bots/`; CI validates it before a merged PR goes live • Grok Bot support – official share links can surface an “Add to Grok Bot” option without rehosting packed configs • Public API and feeds – browse listings with search, category, integration, paging, and sync options It’s open-source (MIT license). Link in the reply 👇view source ↗
-
• twitter 1w neutralThis might have been my best day so far at oai. Ridiculous amounts of fun and intensity. Future is bright This might have been my best day so far at oai. Ridiculous amounts of fun and intensity. Future is brightview source ↗
-
• twitter 1w neutralhttps://t.co/MzwrkvEMJY https://t.co/MzwrkvEMJYview source ↗
-
• twitter 1w positiveLet me show you something crazy. This is Qwen 3.8 27B, and every frame is 1 real equation from the model's actual math. The prompt is easy and thinking is off: we ask what the capital of France is, with a one-word reply. If you think this video is doing math fast, it's actually skipping about 7.2 MILLION equations be… Let me show you something crazy. This is Qwen 3.8 27B, and every frame is 1 real equation from the model's actual math. The prompt is easy and thinking is off: we ask what the capital of France is, with a one-word reply. If you think this video is doing math fast, it's actually skipping about 7.2 MILLION equations between every frame. After all the math, Qwen gives the final answer: "Paris". That one-word answer took 25.8 BILLION equations, and my NVIDIA RTX PRO 6000 Blackwell did it in about 13 milliseconds. This video is 32 billion times slower than the actual GPU. Showing every single equation at one per frame at 60 fps would take over 13 years, for one word. Now imagine scaling that from 27B parameters up to models with hundreds of billions or even trillions of parameters, and that's why AI needs so much compute. Appreciate your GPUs, no matter which one you have. They're actually insane.view source ↗
-
• twitter 1w neutralI actually don't use my 3090s anymore They will become more valuable once smaller models become more intelligent, efficient, and capable For now, they're sitting idle waiting for Qwen 5 27B or something I actually don't use my 3090s anymore They will become more valuable once smaller models become more intelligent, efficient, and capable For now, they're sitting idle waiting for Qwen 5 27B or somethingview source ↗
-
• twitter 1w neutralRT @_overment: "what you send is not what the model gets" example from the first week of @megadevhq: a simple "hi" turns into ~61k token… RT @_overment: "what you send is not what the model gets" example from the first week of @megadevhq: a simple "hi" turns into ~61k token…view source ↗
-
• twitter 1w neutralMayor Nadia Mohamed (D-MN): The way to end Somali gang shootings is to "ban guns" How about denaturalize and deport? https://t.co/CPyiMyAqEz Mayor Nadia Mohamed (D-MN): The way to end Somali gang shootings is to "ban guns" How about denaturalize and deport? https://t.co/CPyiMyAqEzview source ↗
-
• twitter 1w neutralLocation: Founders Inc at Fort Mason https://t.co/zrpaxgfxEs Location: Founders Inc at Fort Mason https://t.co/zrpaxgfxEsview source ↗
-
• twitter 1w negativethis language app made 184M organic views from 14 accounts their format: - crying hook -> app demo - the ai tutor roasts her so the app is the villain and it feels funny - one girl ran it 20 times, her worst one still did 1.5M you can check their entire UGC operation here for free https://t.co/FfDDNRxARw this language app made 184M organic views from 14 accounts their format: - crying hook -> app demo - the ai tutor roasts her so the app is the villain and it feels funny - one girl ran it 20 times, her worst one still did 1.5M you can check their entire UGC operation here for free https://t.co/FfDDNRxARwview source ↗
-
• twitter 1w negativea friend is hiring for an app studio. needs an ai-first operator. ideally an intern to start, with scope to go full-time. - paid. remote. no fixed hours. - your own projects or another job? no issue. - iim/management preferred, not a must. DM's open. a friend is hiring for an app studio. needs an ai-first operator. ideally an intern to start, with scope to go full-time. - paid. remote. no fixed hours. - your own projects or another job? no issue. - iim/management preferred, not a must. DM's open.view source ↗