•twitter5592
listening to
timeline
5592
mentions
tracked
tracked
net sentiment
+24%
1775 positive
3393 neutral
424 negative
volume & sentiment over time
Sep 30 – Oct 5, 2026 · Daily
sources
most discussed
—
active days
6
mentions
Showing 4176–4200 of 5592 mentions
-
• twitter 2d neutralSmall accounts are the hardest workers on 𝕏. Small accounts are the hardest workers on 𝕏.view source ↗
-
• twitter 2d neutralt3 code publicly launched about 7 months ago. julius's orchestrator rewrite was open for just over 4 months. pr #2829 we're now at #14860 823 commits. 1,912 files changed. 83% of the repo's prs were opened after this one. it's finally merged. t3 code publicly launched about 7 months ago. julius's orchestrator rewrite was open for just over 4 months. pr #2829 we're now at #14860 823 commits. 1,912 files changed. 83% of the repo's prs were opened after this one. it's finally merged.view source ↗
-
• twitter 2d positiveWrote a post about Kev 1.0 and how it works https://t.co/QRUq7dtN0A Wrote a post about Kev 1.0 and how it works https://t.co/QRUq7dtN0Aview source ↗
-
• twitter 2d positivewe love to see it $0 in ad spend btw https://t.co/z4rQXLNlL8 we love to see it $0 in ad spend btw https://t.co/z4rQXLNlL8view source ↗
-
• twitter 2d positiveWe had a lot of fun with this one, thanks for the inspiration @venturetwins! Create one for your own pet, product or everyday object. Using your agent in Google Flow, first, create a storyboard outlining your key points in each frame. Then, use your agent to prompt Gemini Omni to craft every scene and effortlessly bri… We had a lot of fun with this one, thanks for the inspiration @venturetwins! Create one for your own pet, product or everyday object. Using your agent in Google Flow, first, create a storyboard outlining your key points in each frame. Then, use your agent to prompt Gemini Omni to craft every scene and effortlessly bring your explainer videos and ads to life.view source ↗
-
• twitter 2d positiveGet one job like this set up for you every month. Run On Claude hands you a ready-to-install Claude job each month, built for small business owners. Not saving you time after 30 days? You get your money back: https://t.co/uD5ob5hpHH Get one job like this set up for you every month. Run On Claude hands you a ready-to-install Claude job each month, built for small business owners. Not saving you time after 30 days? You get your money back: https://t.co/uD5ob5hpHHview source ↗
-
• twitter 2d positive<prompt> <role> You are the front desk for my small business. You answer new leads fast, in my voice, with my real prices. You never invent a price, a date or a promise. </role> <objective> For every new enquiry, sort it and draft the reply I can send from my phone within the hour. </objective> <setup> Ask me once, the… <prompt> <role> You are the front desk for my small business. You answer new leads fast, in my voice, with my real prices. You never invent a price, a date or a promise. </role> <objective> For every new enquiry, sort it and draft the reply I can send from my phone within the hour. </objective> <setup> Ask me once, then remember: 1. What I sell - with my price list 2. Where and when - service area and hours 3. Three past replies - that turned into bookings 4. Jobs I never take </setup> <sort> Put every enquiry in one pile: - Ready - knows what they want, asks when - Pricing - wants a number first - Unclear - needs one question answered - Not a fit - outside what I do </sort> <reply_rules> 1. First line answers their actual question 2. The price from my list, or a range and what changes it 3. Two free times from my calendar 4. One easy next step - Under 90 words. Sound like my examples. </reply_rules> <output_format> 1. The pile, and why 2. The draft reply 3. Anything to check before I send </output_format> <rules> - Draft only. I send every message. - Not a fit gets a kind no, and a referral if you know one. </rules> </prompt>view source ↗
-
• twitter 2d positiveAnswer every new lead within the hour, even mid-job. Paste this into Claude. It reads each new enquiry, sorts it (ready to book, wants a price, not a fit) and drafts the reply in your voice, with your real prices and two free slots from your calendar. You read it on your phone and hit send. The business that replies … Answer every new lead within the hour, even mid-job. Paste this into Claude. It reads each new enquiry, sorts it (ready to book, wants a price, not a fit) and drafts the reply in your voice, with your real prices and two free slots from your calendar. You read it on your phone and hit send. The business that replies first usually gets the job, and it's rarely the cheapest one. Full prompt below:view source ↗
-
• twitter 2d positivehow do you even review something like this how do you even review something like thisview source ↗
-
• twitter 2d neutralSee the live results and dive into the Agent Arena Pareto frontier at: https://t.co/5tUiBcBJkO See the live results and dive into the Agent Arena Pareto frontier at: https://t.co/5tUiBcBJkOview source ↗
-
• twitter 2d neutralClaude Sonnet 5.5 by @AnthropicAI just landed at #3 in the Agent Arena. This model has a median cost per task of $2.74, and a +12.5% net improvement score. Claude Sonnet 5.5 delivers top-tier performance, but at a cost premium: #2 Claude Opus 5.5 costs $1.58 per task while achieving a higher score. That tradeoff keeps… Claude Sonnet 5.5 by @AnthropicAI just landed at #3 in the Agent Arena. This model has a median cost per task of $2.74, and a +12.5% net improvement score. Claude Sonnet 5.5 delivers top-tier performance, but at a cost premium: #2 Claude Opus 5.5 costs $1.58 per task while achieving a higher score. That tradeoff keeps Sonnet 5.5 just off the Agent Arena Pareto frontier.view source ↗
-
• twitter 2d neutralIt happened It happenedview source ↗
-
• twitter 2d neutral@theo curious about the DAU @theo curious about the DAUview source ↗
-
• twitter 2d neutralI’m going to buy a $200 plan. Which one should I choose? - Codex Max plan - Claude Code plan I’m going to buy a $200 plan. Which one should I choose? - Codex Max plan - Claude Code planview source ↗
-
• twitter 2d neutralRT @joshua_xu_: We're the #1 video model on OpenRouter today! https://t.co/IvDpDrTxJ4 RT @joshua_xu_: We're the #1 video model on OpenRouter today! https://t.co/IvDpDrTxJ4view source ↗
-
• twitter 2d neutralDive into the Code Arena: WebDev leaderboard at https://t.co/CY0WQfSRRg Dive into the Code Arena: WebDev leaderboard at https://t.co/CY0WQfSRRgview source ↗
-
• twitter 2d neutralExciting news: Claude Sonnet 5.5 (Max) by @AnthropicAI has debuted at #3 in the Agent Arena with +12.5% net improvement! This release is a 8.1 percentage-point increase over Claude Sonnet 5 (High), which ranks #13 with +4.4% net improvement. By category, Claude Sonnet 5.5 secured the #1 spot in Chat (+15.6%) above bot… Exciting news: Claude Sonnet 5.5 (Max) by @AnthropicAI has debuted at #3 in the Agent Arena with +12.5% net improvement! This release is a 8.1 percentage-point increase over Claude Sonnet 5 (High), which ranks #13 with +4.4% net improvement. By category, Claude Sonnet 5.5 secured the #1 spot in Chat (+15.6%) above both Fable 5.1 (+11.49%) and Opus 5.5 (+10.29%). This performance comes with a higher cost: Claude Sonnet 5.5 (Max) has a median cost of $2.74 per task, about 73% higher than #2 Claude Opus 5.5 (High) at $1.58. @AnthropicAI models now hold all three top positions in Agent Arena. Congrats to the team!view source ↗
-
• twitter 2d neutralThis PR is so big that it takes over 30 seconds for the page to load on Github and it lags if you try to scroll or resize the browser 💀 This PR is so big that it takes over 30 seconds for the page to load on Github and it lags if you try to scroll or resize the browser 💀view source ↗
-
• twitter 2d positive🎉 https://t.co/0ejkYv27yL 🎉 https://t.co/0ejkYv27yLview source ↗
-
• twitter 2d positiveWrote a post about Kev and how it works https://t.co/XnCUUpVAMc Wrote a post about Kev and how it works https://t.co/XnCUUpVAMcview source ↗
-
• twitter 2d 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 2d neutralThis is wild... 🤯 AI companies will need to generate at least $4.2 trillion in new annual revenue by 2031 just to pay for their data center buildout. That’s according to @BainandCompany The AI infrastructure bill is getting very real. This is wild... 🤯 AI companies will need to generate at least $4.2 trillion in new annual revenue by 2031 just to pay for their data center buildout. That’s according to @BainandCompany The AI infrastructure bill is getting very real.view source ↗
-
• twitter 2d positiveit’s a beautiful feeling https://t.co/dKes8joI1G https://t.co/WLevool9y8 it’s a beautiful feeling https://t.co/dKes8joI1G https://t.co/WLevool9y8view source ↗
-
• twitter 2d positiveWe are now entering into an era where any product can be created exactly to a consumer's preferences & needs. I vibe-fabricated a dog door with a wifi-controlled lock, perfectly to the specifications & design of my house. I know nothing about metal fabrication or electrical engineering. It's now getting manufactur… We are now entering into an era where any product can be created exactly to a consumer's preferences & needs. I vibe-fabricated a dog door with a wifi-controlled lock, perfectly to the specifications & design of my house. I know nothing about metal fabrication or electrical engineering. It's now getting manufactured and delivered in 2 weeks -- for almost the same cost if I bought a mass-produced item off-the-shelf.view source ↗
-
• twitter 2d neutralme and Claude building an app at 2am https://t.co/wiDzDACa2c me and Claude building an app at 2am https://t.co/wiDzDACa2cview source ↗