•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 4751–4775 of 4998 mentions
-
• twitter 1w positiveLove the @spottedinprod home page https://t.co/J7GGFleaZ3 Love the @spottedinprod home page https://t.co/J7GGFleaZ3view source ↗
-
• twitter 1w positiveGenuinely asking: whats stopping someone from vibecoding their own AI model like ChatGPT?? Genuinely asking: whats stopping someone from vibecoding their own AI model like ChatGPT??view source ↗
-
• twitter 1w positiveIt has been a while .. Thanks to @atomHQ Hand reg HT 8 months Atom premium https://t.co/BKuS5WRTcp It has been a while .. Thanks to @atomHQ Hand reg HT 8 months Atom premium https://t.co/BKuS5WRTcpview source ↗
-
• twitter 1w positiveLaunched the Calculum macOS app, a free and open source app with 281 calculators ▶︎ Works offline, results update as you type ▶︎ Save calculations with ⌘S, compare two side by side ▶︎ Run any calculator in Terminal with the calculum command https://t.co/DZ7vV6lUJ6 https://t.co/BMZk5HFOw2 Launched the Calculum macOS app, a free and open source app with 281 calculators ▶︎ Works offline, results update as you type ▶︎ Save calculations with ⌘S, compare two side by side ▶︎ Run any calculator in Terminal with the calculum command https://t.co/DZ7vV6lUJ6 https://t.co/BMZk5HFOw2view source ↗
-
• twitter 1w positiveI've committed a grave sin, OMP + local models in t3code. I actually love the UI localstudio v2 gonna be just t3code w my stuff slapped on, if it works with t3link it's gg fr I don't want to be building harnesses, nor jumping around them anymore. https://t.co/QhiH0aloF2 I've committed a grave sin, OMP + local models in t3code. I actually love the UI localstudio v2 gonna be just t3code w my stuff slapped on, if it works with t3link it's gg fr I don't want to be building harnesses, nor jumping around them anymore. https://t.co/QhiH0aloF2view source ↗
-
• twitter 1w positive@Tiny_Fish @PhotonHQ Awesome @Tiny_Fish @PhotonHQ Awesomeview source ↗
-
• twitter 1w positivePlanning to spend my long weekend helping GenZ who are working through the weekend. If you're proud of the work you are doing and looking for internships, fill this form by Saturday midnight - https://t.co/voxP7ebR7k. Will reply to everyone within 72 hours; will either offer an internship or intro you to other founde… Planning to spend my long weekend helping GenZ who are working through the weekend. If you're proud of the work you are doing and looking for internships, fill this form by Saturday midnight - https://t.co/voxP7ebR7k. Will reply to everyone within 72 hours; will either offer an internship or intro you to other founders who are hiring.view source ↗
-
• twitter 1w positiveClaim your free $50 Render credits from hactober fest site 😋 link : https://t.co/lMq8kLzX8W https://t.co/YXNa9G1C8o Claim your free $50 Render credits from hactober fest site 😋 link : https://t.co/lMq8kLzX8W https://t.co/YXNa9G1C8oview source ↗
-
• twitter 1w positiveI need a cool startup name for my next project, any ideas? 🤔 https://t.co/zI7Tp79H94 I need a cool startup name for my next project, any ideas? 🤔 https://t.co/zI7Tp79H94view source ↗
-
• twitter 1w positivemarket saturation excites me it means there are already people making serious money selling the exact service you want to sell so you don't have to experiment. understand why they're winning, add your own personality, promote yourself shamelessly and become one of the winners market saturation excites me it means there are already people making serious money selling the exact service you want to sell so you don't have to experiment. understand why they're winning, add your own personality, promote yourself shamelessly and become one of the winnersview source ↗
-
• twitter 1w positiveRT @badlogicgames: it's very nice to wake up to lots of positive feedback. cheers! RT @badlogicgames: it's very nice to wake up to lots of positive feedback. cheers!view source ↗
-
• twitter 1w positiveI just got my first CVE - a CVSS 8.8 memory corruption bug in Ghost! I read about HEIF Heist last week, and how it affected libheif. libheif is bundled in libvips, which is bundled in sharp, a popular Node.js image processing library. Patches exist, but users must update the dependency To repro the issue, I got Min… I just got my first CVE - a CVSS 8.8 memory corruption bug in Ghost! I read about HEIF Heist last week, and how it affected libheif. libheif is bundled in libvips, which is bundled in sharp, a popular Node.js image processing library. Patches exist, but users must update the dependency To repro the issue, I got MiniMax M3 to build a working PoC image file and script. It also took advantage of some loose file extension logic to bypass mime type checks. The repro reliably crashes the container, and there's possibly room for code execution too Super fun, very cool what you can do with AI now! 🤩view source ↗
-
• twitter 1w positiveThis is a goldmine for every designer. 👀 Reelfolio makes it ridiculously easy to turn your designs into beautiful animated showreels. Check it out → https://t.co/Ay2dOoYhs0 https://t.co/cLv2LLeCG8 This is a goldmine for every designer. 👀 Reelfolio makes it ridiculously easy to turn your designs into beautiful animated showreels. Check it out → https://t.co/Ay2dOoYhs0 https://t.co/cLv2LLeCG8view source ↗
-
• twitter 1w positiveAndrej Karpathy makes a good point: as AI does more of the work, more of your job becomes reading what it produces. His first tip caught my eye. Ask the model to explain things in ASD-STE100. ASD-STE100 is a controlled English standard built for aircraft maintenance manuals. A mechanic anywhere in the world should re… Andrej Karpathy makes a good point: as AI does more of the work, more of your job becomes reading what it produces. His first tip caught my eye. Ask the model to explain things in ASD-STE100. ASD-STE100 is a controlled English standard built for aircraft maintenance manuals. A mechanic anywhere in the world should read a step once and get it right. The core rules: 1. Keep sentences short 2. One action per step 3. Say who does what 4. Give each thing one name and stick to it AI output breaks that last rule all the time. It says "worker," then "agent," then "executor," and you can't tell if it means one component or three. The full spec is strict. Karpathy asks for "80% of the way," and that works for daily use. Someone turned it into an open-source skill: https://t.co/FFqEehqVl2view source ↗
-
• twitter 1w positiveGitHub actions are a super easy way to get started with software factories 1. Essentially free sandboxes for public repo's 2. You already have a login 3. Create tickets (pieces of work for the agent to do) as issues 4. Use labels to trigger actions, which create PR's 5. Actions can apply labels, which create loops 6. … GitHub actions are a super easy way to get started with software factories 1. Essentially free sandboxes for public repo's 2. You already have a login 3. Create tickets (pieces of work for the agent to do) as issues 4. Use labels to trigger actions, which create PR's 5. Actions can apply labels, which create loops 6. Cron jobs (albeit not very accurate) for running daily jobs 7. Simple observability for seeing what went wrong Great for messing about with software factories before building them on your own infraview source ↗
-
• twitter 1w positiveAlexandr Wang on enterprise perception ▫️Better products can still lose ▫️Big buyers rarely confront reality ▫️Palantir gave hires an acting book Wang: Perception is more real than reality https://t.co/bTIO4gbMN5 Alexandr Wang on enterprise perception ▫️Better products can still lose ▫️Big buyers rarely confront reality ▫️Palantir gave hires an acting book Wang: Perception is more real than reality https://t.co/bTIO4gbMN5view source ↗
-
• twitter 1w positiveHello to all my new connections! Quick reintro: I’m Chris. 44. UK based. Coffee-fuelled. I write about building-in-public, AI, tech, sci-fi. I’m currently building and shipping PulseWatch, a lightweight monitor for solo developers. If you’re interested in any of the above, don’t be a stranger. Would love to conn… Hello to all my new connections! Quick reintro: I’m Chris. 44. UK based. Coffee-fuelled. I write about building-in-public, AI, tech, sci-fi. I’m currently building and shipping PulseWatch, a lightweight monitor for solo developers. If you’re interested in any of the above, don’t be a stranger. Would love to connect.view source ↗
-
• twitter 1w positiveI Thank Netflix, for another masterpiece... 10/10 👑🍿🔥 https://t.co/yOJyWxToyr I Thank Netflix, for another masterpiece... 10/10 👑🍿🔥 https://t.co/yOJyWxToyrview source ↗
-
• twitter 1w positiveDude I just realised my vllm article was liked by the guy himself at @vllm_project 🥹🥹 https://t.co/Z6frzLoQX7 Dude I just realised my vllm article was liked by the guy himself at @vllm_project 🥹🥹 https://t.co/Z6frzLoQX7view source ↗
-
• twitter 1w positiveANTHROPIC JUST MADE CLAUDE CODE WAY MORE CUSTOMIZABLE. With Claude Code mods, you can now customize how Claude Code looks and works just by prompting it 🤯 A mod is a small JS or TS file that runs inside your session. It can: > watch sessions > modify context > handle commands > block tool calls > and even render UI!… ANTHROPIC JUST MADE CLAUDE CODE WAY MORE CUSTOMIZABLE. With Claude Code mods, you can now customize how Claude Code looks and works just by prompting it 🤯 A mod is a small JS or TS file that runs inside your session. It can: > watch sessions > modify context > handle commands > block tool calls > and even render UI! You don’t need to master the API either. Describe what you want, let Claude build it, and share the result as a plugin. I added the full write-up by ex-Googler @addyosmani in the 🧵↓view source ↗
-
• twitter 1w positiveMake your next UI look 10x better with these component libraries: Annnimate https://t.co/sWH94T1K2W UseLayouts https://t.co/d1xPQZaf2V Arc UI https://t.co/jMGNVpbPmv Kobra Systems https://t.co/KeNapqlLIE Bencho https://t.co/aLIQnv1nai HyperUIX https://t.co/ifmVjKbkFS Libraries Dev https://t.co/1GeiJ58EYA BeUI … Make your next UI look 10x better with these component libraries: Annnimate https://t.co/sWH94T1K2W UseLayouts https://t.co/d1xPQZaf2V Arc UI https://t.co/jMGNVpbPmv Kobra Systems https://t.co/KeNapqlLIE Bencho https://t.co/aLIQnv1nai HyperUIX https://t.co/ifmVjKbkFS Libraries Dev https://t.co/1GeiJ58EYA BeUI https://t.co/n7lD6DIrxR BeautifulUI https://t.co/Mj8n2z2cx5 UI Maxxing https://t.co/zJeKIPuq4Uview source ↗
-
• twitter 1w positiveMobilerun just beat GOOGLE’S ARTEMIS on AndroidWorld🤯🔥 116/116 tasks completed. The benchmark spans 20 Android apps and tests agents on real, multi-step mobile workflows. Google Artemis - 99%+ Mobilerun AI - 100% Mobile agents are getting really good. And this is just the beginning. Mobilerun just beat GOOGLE’S ARTEMIS on AndroidWorld🤯🔥 116/116 tasks completed. The benchmark spans 20 Android apps and tests agents on real, multi-step mobile workflows. Google Artemis - 99%+ Mobilerun AI - 100% Mobile agents are getting really good. And this is just the beginning.view source ↗
-
• twitter 1w positiveUsers are Paying for https://t.co/E1S5do9bpg 😀 Won't let their trust go down. Implemented Posthog Support Widget for near instant help at any step :) Clean your mailbox now with https://t.co/E1S5do9bpg https://t.co/4OAi8Ad33g Users are Paying for https://t.co/E1S5do9bpg 😀 Won't let their trust go down. Implemented Posthog Support Widget for near instant help at any step :) Clean your mailbox now with https://t.co/E1S5do9bpg https://t.co/4OAi8Ad33gview source ↗
-
• twitter 1w positivethis was actually a good resource https://t.co/nHkwqP6HUM this was actually a good resource https://t.co/nHkwqP6HUMview source ↗
-
• twitter 1w positive$150 in free Meta Model API credits for every hackathon participant. Applications open soon. Meta is announcing a global AI hackathon: 10 days, $1M cash prize pool, virtual and free, open worldwide. Meta Model API includes: • Muse Spark 1.3: ~35M output tokens for $150 • Muse Spark 1.3 Contributor: ~750M output toke… $150 in free Meta Model API credits for every hackathon participant. Applications open soon. Meta is announcing a global AI hackathon: 10 days, $1M cash prize pool, virtual and free, open worldwide. Meta Model API includes: • Muse Spark 1.3: ~35M output tokens for $150 • Muse Spark 1.3 Contributor: ~750M output tokens for $150 (prompts improve Meta's products) • Muse Image • Muse Voice Transcribe • SAM 3.1 Not open yet. Sign up to get notified 👇 https://t.co/BL7JuhSaI3view source ↗