•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 2676–2700 of 4998 mentions
-
• twitter 1w positiveAnother beautiful day to remind you that I'm a visual and brand identity designer ❤️. I create identities and visual systems for business, startups and brands to help them stand out and attract their target audience. Let's work on your next project ☺️. https://t.co/w48S3KfxTU Another beautiful day to remind you that I'm a visual and brand identity designer ❤️. I create identities and visual systems for business, startups and brands to help them stand out and attract their target audience. Let's work on your next project ☺️. https://t.co/w48S3KfxTUview source ↗
-
• twitter 1w positiveHey folks at @orca_build, could you please improve ChatUI, especially on mobile? I know it’s still experimental, but it would be great to see it become more stable soon. Thanks in advance! Hey folks at @orca_build, could you please improve ChatUI, especially on mobile? I know it’s still experimental, but it would be great to see it become more stable soon. Thanks in advance!view source ↗
-
• twitter 1w positiveI'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > … I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article belowview source ↗
-
• twitter 1w positiveThank you @x : 20->180 followers in 2 days! Looking to connect with: • founder • marketer, growth • indie hacker, builder • saas • live in France Let’s connect👋 https://t.co/uyDK9Kxrpl Thank you @x : 20->180 followers in 2 days! Looking to connect with: • founder • marketer, growth • indie hacker, builder • saas • live in France Let’s connect👋 https://t.co/uyDK9Kxrplview source ↗
-
• twitter 1w positiveOpus 5.5 built a working Chrome extension in 1.5 minutes that fixes GitHub screenshots opening in a new tab instead of inline, and it still feels magical that you can just describe an annoyance and have it fixed. https://t.co/X1l6YJb9hl Opus 5.5 built a working Chrome extension in 1.5 minutes that fixes GitHub screenshots opening in a new tab instead of inline, and it still feels magical that you can just describe an annoyance and have it fixed. https://t.co/X1l6YJb9hlview source ↗
-
• twitter 1w positivenever work in a startup where founder’s family members are also working never work in a startup where founder’s family members are also workingview source ↗
-
• twitter 1w positiveKeep learning. Keep growing. Keep winning. Keep learning. Keep growing. Keep winning.view source ↗
-
• twitter 1w positiveHermes, at home in Tern ☤ A native Tern frontend for Hermes Agent. Same hermes command, but replies are written in gold ink that dries, tools and subagents stream live, and every turn ends ☤ delivered. Thanks @NousResearch and @_can1357 https://t.co/qTLG2cTKRj Hermes, at home in Tern ☤ A native Tern frontend for Hermes Agent. Same hermes command, but replies are written in gold ink that dries, tools and subagents stream live, and every turn ends ☤ delivered. Thanks @NousResearch and @_can1357 https://t.co/qTLG2cTKRjview source ↗
-
• twitter 1w positiveThe serious answer to how Shazam worked is it took the peaks of a spectrogram of short clips of every song, find the peaks from the highest amplitude bits, hash it with the value being (time stamp, track id) and then the actual recognition is a hashtable lookup. We did this for a college CS project. The original paper… The serious answer to how Shazam worked is it took the peaks of a spectrogram of short clips of every song, find the peaks from the highest amplitude bits, hash it with the value being (time stamp, track id) and then the actual recognition is a hashtable lookup. We did this for a college CS project. The original paper is fantastic:view source ↗
-
• twitter 1w positiveNot website. But Opal hands down got the best UI on the entire App Store. https://t.co/BmmDDpzGCO Not website. But Opal hands down got the best UI on the entire App Store. https://t.co/BmmDDpzGCOview source ↗
-
• twitter 1w positiveif you're getting into game design, there are so many good resources out there to learn from! if you're getting into game design, there are so many good resources out there to learn from!view source ↗
-
• twitter 1w positivethe original study, free to read (Brynjolfsson, Li & Raymond, "Generative AI at Work", published in the Quarterly Journal of Economics, 2025): https://t.co/6jlWEFZf9O the original study, free to read (Brynjolfsson, Li & Raymond, "Generative AI at Work", published in the Quarterly Journal of Economics, 2025): https://t.co/6jlWEFZf9Oview source ↗
-
• twitter 1w positiveStanford's Erik Brynjolfsson and two MIT economists tracked 5,179 support agents to see who AI actually helps. the experts barely moved. the beginners got 34% more productive. agents 2 months in, with AI, performed like agents 6+ months in without it. this 2-page PDF breaks down the study, and why being new is where… Stanford's Erik Brynjolfsson and two MIT economists tracked 5,179 support agents to see who AI actually helps. the experts barely moved. the beginners got 34% more productive. agents 2 months in, with AI, performed like agents 6+ months in without it. this 2-page PDF breaks down the study, and why being new is where the biggest gains showed up. the real question isn't "am I too late to start with AI?" it's "how big is my head start if I set AI up now?" the skill that turns that head start into a one-person company is in the article below:view source ↗
-
• twitter 1w positive@davis7 I see no issue here (and I can still mostly see) @davis7 I see no issue here (and I can still mostly see)view source ↗
-
• twitter 1w positiveDots, Grok Bot, or Muse? I'm starting to use Dots and it's not bad - free compute. Dots, Grok Bot, or Muse? I'm starting to use Dots and it's not bad - free compute.view source ↗
-
• twitter 1w positiveI can’t believe how hard it is to make something even decent. Unbelievable. I can’t believe how hard it is to make something even decent. Unbelievable.view source ↗
-
• twitter 1w positiveHow many followers do you need on X to stay motivated and start making good money? A) 1K–5K B) 5K–10K C) 10K–50K D) 50K+ How many followers do you need on X to stay motivated and start making good money? A) 1K–5K B) 5K–10K C) 10K–50K D) 50K+view source ↗
-
• twitter 1w positiveUnpopular opinion: a boring app with a hard paywall beats a beautiful app with a free tier every time. Unpopular opinion: a boring app with a hard paywall beats a beautiful app with a free tier every time.view source ↗
-
• twitter 1w positiveI made 104 demo videos in 40 minutes, and I didn't record a single one. Claude did. 🤯 https://t.co/5hDIulx6OL is a Chrome extension with 52 developer tools 🛠️, and every tool needs a "how to use" demo, plus a vertical version for TikTok and Reels (52 + 52 = 104). Doing that by hand means 2-3 days of screen recording,… I made 104 demo videos in 40 minutes, and I didn't record a single one. Claude did. 🤯 https://t.co/5hDIulx6OL is a Chrome extension with 52 developer tools 🛠️, and every tool needs a "how to use" demo, plus a vertical version for TikTok and Reels (52 + 52 = 104). Doing that by hand means 2-3 days of screen recording, endless retakes, my tired voice at 2am 😴, and so-so quality at the end. I didn't want to do any of that. So I gave the whole job to Claude Opus 5.5 🤖. It opened a real Chrome browser on my Mac, installed my extension locally, and used all 52 tools like a real person, with smooth cursor movement, clicks and typing 🖱️ It logged every step with exact timestamps, wrote a script for each demo, voiced it, and put the final videos together 🎬. I just watched ☕ The stack 👇 🎭 Playwright: drives the browser and records the demos 🧱 HTML: draws every frame (captions, overlays, a talking mascot) 🎞️ ffmpeg: joins video and audio 🗣️ Kokoro: free text-to-speech that runs locally, no API key No video editor, no paid voice service, no recording software 🙅♂️ The part I love most ❤️ Kokoro gives the timing of every spoken word, so the mascot's mouth lip-syncs to the voiceover automatically. Even the background music is generated in code 🎵 so there's nothing to license. Here's one of the demos 👇view source ↗
-
• twitter 1w positiveit's been just under a week of using dots, and a day or so of using grokbot (courtesy of @poteto, pinging @thsottiaux so you guys can continue sparring). the tl;dr of my adventure so far: why not both? - grokbot works better out of the box. dots are a little finnicky to set up and onboard onto tasks, and requires a l… it's been just under a week of using dots, and a day or so of using grokbot (courtesy of @poteto, pinging @thsottiaux so you guys can continue sparring). the tl;dr of my adventure so far: why not both? - grokbot works better out of the box. dots are a little finnicky to set up and onboard onto tasks, and requires a little struggle to get it working as intended - dots do get better over time, more considerably than grokbot. might be because the baseline starts lower, but i like that dots are very adaptable to requests that you make - multiple bots > one dot. i think that oai should've shipped multiple dots at once, because it really helps with personal context switching - dots have really good integration into daily life stuff (gcal, gmail etc), but lack some important integrations (discord, x) that i would love to see - dots are getting better day by day. i might be tripping but i keep seeing minor UI improvements show up unannounced which i appreciate greatly - pstack. compliments to the chef. i have it ported over to dots and it is still incredible (even with all the hacks i did to get it working). will daily drive it on pi going forward - you can always use both! if you use both dots and grokbot, you can have two VMs for (essentially) free. i'll be posting soon about how you can add both VMs to cua spaces and expand your compute - i currently have grokbot focused more on the X integration and monitoring social medias, while dots are focused more on coding and monitoring my slack - i really, really want a grokbot/dot equivalent that runs on pi durable. extensible botdot sounds incredibleview source ↗
-
• twitter 1w positiveUpdate: @shl and @gumroad has reached out and we are working on unwinding of investment. More to follow. Update: @shl and @gumroad has reached out and we are working on unwinding of investment. More to follow.view source ↗
-
• twitter 1w positiveThe Great Unsubscription: Why Leaving Became the Only Honest Choice The Observable Pattern In 2026, people are walking away from platforms not because of scandals but because the math stopped working The Great Unsubscription: Why Leaving Became the Only Honest Choice The Observable Pattern In 2026, people are walking away from platforms not because of scandals but because the math stopped workingview source ↗
-
• twitter 1w positiveEarly in my career, I worked with a Chinese intern who did 2x my work, better She was on her 5th internship (common in 🇨🇳) while I was on my 1st job. She was better than me in every work-skill dimension: time management, note taking, prioritisation etc I was mediocre, forced to improve Early in my career, I worked with a Chinese intern who did 2x my work, better She was on her 5th internship (common in 🇨🇳) while I was on my 1st job. She was better than me in every work-skill dimension: time management, note taking, prioritisation etc I was mediocre, forced to improveview source ↗
-
• twitter 1w positiveClaude Just Turned One Keyword Into Five Ranking Articles Digital entrepreneurs can now build ranking content ridiculously faster. https://t.co/wRv8RObR4h Claude transforms one keyword into five genuinely different articles. Real case studies keep every article useful and trustworthy. Prices increase soon, so secu… Claude Just Turned One Keyword Into Five Ranking Articles Digital entrepreneurs can now build ranking content ridiculously faster. https://t.co/wRv8RObR4h Claude transforms one keyword into five genuinely different articles. Real case studies keep every article useful and trustworthy. Prices increase soon, so securing your session now matters. Sign up now before you miss out completely. ✅ Get a custom visibility plan built around opportunities. ✅ Discover competitor gaps hiding profitable ranking opportunities today. ✅ Stronger rankings need authority signals supporting your best content. ✅ Premium backlink opportunities are available for stronger authority growth. ✅ Only a few strategy session spots remain available today. ✅ Your plan includes a fourteen day money back guarantee. ✅ Skip expensive guesswork and leave knowing your next moves. Get a FREE SEO Strategy Session here https://t.co/wRv8RObR4hview source ↗
-
• twitter 1w positiveAs a fellow bully and @bluebottleroast lover, I can confirm this works As a fellow bully and @bluebottleroast lover, I can confirm this worksview source ↗