•twitter5128
listening to
timeline
5128
mentions
tracked
tracked
net sentiment
+24%
1601 positive
3147 neutral
380 negative
volume & sentiment over time
Sep 30 – Oct 5, 2026 · Daily
sources
most discussed
—
active days
6
mentions
Showing 401–425 of 1601 mentions
-
• twitter 20h positiveChatGPT’s new updates could save you hours of busywork. Give it a job, then review the work. Here’s the workflow shown in this video: → Use GPT 6.1 Sol to plan a hard task. → Put your files and project notes in a Space. → Turn useful chats into editable Pages. → Give a Dot a clear goal for ongoing work. → Connec… ChatGPT’s new updates could save you hours of busywork. Give it a job, then review the work. Here’s the workflow shown in this video: → Use GPT 6.1 Sol to plan a hard task. → Put your files and project notes in a Space. → Turn useful chats into editable Pages. → Give a Dot a clear goal for ongoing work. → Connect the apps it needs and set its permissions. → Check its progress and steer the next step. Try a small job first: find five SEO problems on your site and build a fix plan. That gives you something useful to review. Save this video, you’ll have a clear first task to try. Want the SOP? DM me. 💬view source ↗
-
• twitter 20h positiveFable 5.5 made this oil painting and the timelapse Holy shit this is the first model with creativity like this, i fully believe Anthropic did something insane with the 5.5 series. https://t.co/Gcs17Lq4FO Fable 5.5 made this oil painting and the timelapse Holy shit this is the first model with creativity like this, i fully believe Anthropic did something insane with the 5.5 series. https://t.co/Gcs17Lq4FOview source ↗
-
• twitter 20h positiveAI SEO helped one of my sites grow from about 4 to 284 clicks a day. Here’s the workflow behind that case study. It runs inside my Agent OS: → Find keywords getting impressions but few clicks. → Choose a topic worth investigating. → Add a real case study to the brief. → Generate distinct articles for relevant web… AI SEO helped one of my sites grow from about 4 to 284 clicks a day. Here’s the workflow behind that case study. It runs inside my Agent OS: → Find keywords getting impressions but few clicks. → Choose a topic worth investigating. → Add a real case study to the brief. → Generate distinct articles for relevant websites. → Review the pages and track their results. The system gives me one place to see sites, keywords, and drafts. The reported growth is one site’s result, not a promise for every website. Save this video, you’ll see how I turn search data into a content plan. Want the SOP? DM me. 💬view source ↗
-
• twitter 20h positiveTopics to prepare for AI engineering interviews in 2026: - How LLMs work: tokens, embeddings, attention, context windows - Prompting: system prompts, few-shot, structured outputs - RAG: chunking, embeddings, vector search, reranking - Hybrid search: keyword + semantic - Agents: tool calling, planning, loops, stopping … Topics to prepare for AI engineering interviews in 2026: - How LLMs work: tokens, embeddings, attention, context windows - Prompting: system prompts, few-shot, structured outputs - RAG: chunking, embeddings, vector search, reranking - Hybrid search: keyword + semantic - Agents: tool calling, planning, loops, stopping conditions - MCP: building and connecting tool servers - Memory: short-term, long-term, summarization - Evals: golden datasets, LLM-as-judge, regression tests - Hallucinations: how to detect and reduce them - Guardrails: schema validation, output filters - Security: prompt injection, PII, sandboxing tools - Model selection: when to use small vs reasoning models - Cost: tokens, caching, routing, batching - Latency: streaming, speculative decoding, KV cache - Fine-tuning: LoRA, when it beats prompting - Preference tuning: RLHF vs DPO basics - Observability: tracing every model and tool call - Deployment: APIs, queues, retries, rate limits - Reliability: fallbacks, timeouts, resumable workflows - Multimodal: images, audio, documents - System design: design a support agent, a coding agent, a RAG app - Python + async, plus one framework you know deeply - Past project deep dive: what broke and how you fixed it Most interviews end with "show me something you built." Bookmark this + send it to someone prepping for AI interviews.view source ↗
-
• twitter 20h positiveClaude looked like this in 2023. 3 years ago. https://t.co/qHjzURCEnV Claude looked like this in 2023. 3 years ago. https://t.co/qHjzURCEnVview source ↗
-
• twitter 20h positiveHiring at Supabase !! There are 60 open positions across engineering, sales, design, and many more, so there should be something that would fit you! This is a remote company, so where you live doesn't matter. If you are awesome at what you do, you are in. apply here: https://t.co/y1DWWtJ4hU Hiring at Supabase !! There are 60 open positions across engineering, sales, design, and many more, so there should be something that would fit you! This is a remote company, so where you live doesn't matter. If you are awesome at what you do, you are in. apply here: https://t.co/y1DWWtJ4hUview source ↗
-
• twitter 21h positiveWho better to break down Ghost of Yōtei's new Echoes of Sekigahara expansion than Atsu herself? Ghost of Yōtei Complete Edition is out now, with a digital upgrade for owners of the base game: https://t.co/LtGrFs7chf https://t.co/20A3btEy1x Who better to break down Ghost of Yōtei's new Echoes of Sekigahara expansion than Atsu herself? Ghost of Yōtei Complete Edition is out now, with a digital upgrade for owners of the base game: https://t.co/LtGrFs7chf https://t.co/20A3btEy1xview source ↗
-
• twitter 21h positiveJev is getting a lot of attention right now. But after looking through the projects people are actually building with it, I think the more interesting story is not Jev itself. It’s the role it can play inside an agent. A few examples stood out to me: 1. browser-use/jev-ultrafast (~16.6k⭐) Jev picks the next browser… Jev is getting a lot of attention right now. But after looking through the projects people are actually building with it, I think the more interesting story is not Jev itself. It’s the role it can play inside an agent. A few examples stood out to me: 1. browser-use/jev-ultrafast (~16.6k⭐) Jev picks the next browser action without needing another expensive LLM call. https://t.co/bP7kF81nDp 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide which context is still useful and what can be dropped. https://t.co/KKxtr9VY2s 3. TheoLeeCJ/SemIf (~4k⭐) An open-source, local implementation of Jev-style decision making. https://t.co/4iltOQv3o3 4. jarrodwatts/jev-trader (~2.1k⭐) A real-time trading loop where Jev chooses between buy, sell, or wait. https://t.co/3fkfATZKZH 5. kerpopule/hermes-jev-skills (~670⭐) Uses Jev for routing, memory, compaction, and skill selection. https://t.co/WGyDQgfXPM 6. devagrawal09/jev-review (~570⭐) Code review where Jev helps make decisions instead of relying on one massive prompt. https://t.co/YwwJyBsCB2 7. thruwire/foreman (~520⭐) Uses Jev as a supervisor for coding agents: continue, retry, verify, or stop. https://t.co/tky1ts5ZTb 8. superagents-lab/jev-search (~400⭐) Jev decides where an agent should search and how it should search. https://t.co/ALjXzRcJcp 9. droidrun/mobile-jev (~350⭐) Uses Jev to choose the next action for Android agents. https://t.co/yP78qz9sVc 10. gargpratyush/jev-router (~340⭐) Uses Jev to route different agent tasks to the right model. https://t.co/JBYI4N8LOu The pattern across these projects is pretty interesting: 1. LLMs generate. 2. Agents execute. 3. Jev decides. And that decision layer can show up in very different places: → Which action should the agent take? → Which context should it keep? → Which skill should it use? → Which model should handle the task? → Should it retry, verify, or stop? → Where should it search next? This is probably the most useful way to think about Jev. Not as anview source ↗
-
• twitter 21h positivejoin 15k founders using my system, plus one email per week (it's free) https://t.co/7RJApYSStw join 15k founders using my system, plus one email per week (it's free) https://t.co/7RJApYSStwview source ↗
-
• twitter 21h positiveThanks @andy_murray, @DavidFerrer87, @richardgasquet1 , @fabiofogna, @domithiem, @Charlymoya and Marat for sharing this special day with me and with all the fans. A day we will never forget at the @rnadalacademy! https://t.co/X1OeoDtvoL Thanks @andy_murray, @DavidFerrer87, @richardgasquet1 , @fabiofogna, @domithiem, @Charlymoya and Marat for sharing this special day with me and with all the fans. A day we will never forget at the @rnadalacademy! https://t.co/X1OeoDtvoLview source ↗
-
• twitter 21h positiveyou can give Claude Code MUCH better browser use with one plugin... because browser control is where Anthropic's harness falls behind Codex it's slow and inaccurate, while Codex moves fast and does more than the job most of the time so install Browser Use CLI... Claude Code stops fumbling the browser and starts keep… you can give Claude Code MUCH better browser use with one plugin... because browser control is where Anthropic's harness falls behind Codex it's slow and inaccurate, while Codex moves fast and does more than the job most of the time so install Browser Use CLI... Claude Code stops fumbling the browser and starts keeping up not sponsored, i genuinely love the product and i've been on the Cloud option for months, it's really good with Opus 5.5 paste this into Claude Code: ---------------- "install or upgrade browser-use․com to the latest stable version with uv using Python, run `browser-use skill install` to register the skill, and connect it to my browser. If setup or connection fails, follow their official github"view source ↗
-
• twitter 21h positiveWant to digest stocks like a hedgefund? Connect your Muse with Unusual Whales. Take a look below. https://t.co/F4P27wB1Nw Want to digest stocks like a hedgefund? Connect your Muse with Unusual Whales. Take a look below. https://t.co/F4P27wB1Nwview source ↗
-
• twitter 21h positiveHey friends! How's the weekend going? ✨ Are you building or touching grass? Maybe touching grass AND agents building at home or a VPS? 😆 Did you know Orca has native integrations for GitHub, GitLab, Linear and Jira?! Using them? Running automations? Any feedback? 🙏 https://t.co/VH1eMMvcuI Hey friends! How's the weekend going? ✨ Are you building or touching grass? Maybe touching grass AND agents building at home or a VPS? 😆 Did you know Orca has native integrations for GitHub, GitLab, Linear and Jira?! Using them? Running automations? Any feedback? 🙏 https://t.co/VH1eMMvcuIview source ↗
-
• twitter 21h positivewho else just wants the football players to have a good time? who else just wants the football players to have a good time?view source ↗
-
• twitter 21h positiveA week of Claude Code sessions is too much to remember. Every weekend, have Opus 5.5 vibe-code a quick 𝘄𝗲𝗲𝗸𝗹𝘆 𝗰𝗮𝗹𝗲𝗻𝗱𝗮𝗿 like this from your local session logs. Then give it 𝗮 𝘀𝘂𝗯𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗼𝗻𝗹𝘆 𝗯𝘂𝗶𝗹𝗱𝘀 𝘄𝗲𝗲𝗸𝗹𝘆 𝗰𝗮𝗹𝗲𝗻𝗱𝗮𝗿𝘀: → Name it week-calendar, set its effort to medium, and preload a design skill → The first time, it as… A week of Claude Code sessions is too much to remember. Every weekend, have Opus 5.5 vibe-code a quick 𝘄𝗲𝗲𝗸𝗹𝘆 𝗰𝗮𝗹𝗲𝗻𝗱𝗮𝗿 like this from your local session logs. Then give it 𝗮 𝘀𝘂𝗯𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗼𝗻𝗹𝘆 𝗯𝘂𝗶𝗹𝗱𝘀 𝘄𝗲𝗲𝗸𝗹𝘆 𝗰𝗮𝗹𝗲𝗻𝗱𝗮𝗿𝘀: → Name it week-calendar, set its effort to medium, and preload a design skill → The first time, it asks which colors you like and whether to color by project or by task, and saves that to memory. After that, every calendar follows it → Call it when you want to look back on the week or write a weekly report. It regenerates the calendar and writes up a 3-line weekly report for you → The calendar shows four things: when you worked each day, what each session did, 𝘄𝗵𝗶𝗰𝗵 𝘀𝗲𝘀𝘀𝗶𝗼𝗻𝘀 𝘀𝘁𝗼𝗽𝗽𝗲𝗱 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗮 𝘀𝗶𝗻𝗴𝗹𝗲 𝗰𝗼𝗺𝗺𝗶𝘁, and how many hours each project took this week Send this prompt to Claude Code 👇 "Set up a subagent that only builds weekly calendars: 1. Create week-calendar in ~/.claude/agents: model: opus, effort: medium, memory: user. Preload the design skills I have installed (for example impeccable). Give it Bash so it can run git log and the script that builds the calendar. It only writes files to ~/.calendar/ and its own memory. 2. The first time, it asks me what style I like: dark or light, one accent color, color by project or by task type, and whether the week starts on Monday or Sunday. It saves my answers to memory and follows them every time. 3. The calendar is one HTML file. The script writes the data straight into it, so it opens with a double-click. Use this week's session logs: Claude Code's are in ~/.claude/projects/ (skip the subagents folders), and if I use Codex, add ~/.codex/sessions/. Before writing the script, open one file to check the fields. Convert times to my local time zone, and use the cwd in each record to tell projects apart. One block per session; start a new block after any gap longer than 30 minutes. Clicking a block shows the project, start and end time, the model used, the session title (if there isn't one, sum up my firstview source ↗
-
• twitter 21h positiveHey there! I’m Prerona 🫶🏼 the content head of @gojiberryai If you’re in ✅ Marketing ✅ AI ✅ GTM And your playlist is mostly filled with millennial bangers then I’d really really love to connect :) https://t.co/kJyZyM0cJ3 Hey there! I’m Prerona 🫶🏼 the content head of @gojiberryai If you’re in ✅ Marketing ✅ AI ✅ GTM And your playlist is mostly filled with millennial bangers then I’d really really love to connect :) https://t.co/kJyZyM0cJ3view source ↗
-
• twitter 21h positive$1500 revenue in one month and 19 acquisition offers on trustmrr CodeHype is going crazy !! Launch your startup on https://t.co/c3gBhz19tR to get discovered by google & llms + Get a free dofollow backlink https://t.co/R2r9VQg4Jc $1500 revenue in one month and 19 acquisition offers on trustmrr CodeHype is going crazy !! Launch your startup on https://t.co/c3gBhz19tR to get discovered by google & llms + Get a free dofollow backlink https://t.co/R2r9VQg4Jcview source ↗
-
• twitter 21h positiveGrok Bot is growing insanely fast. just brought @bot to 🇰🇿🇰🇬🇺🇿🇦🇿🇬🇪 thanks, @elonmusk https://t.co/SAIgPe7Duo Grok Bot is growing insanely fast. just brought @bot to 🇰🇿🇰🇬🇺🇿🇦🇿🇬🇪 thanks, @elonmusk https://t.co/SAIgPe7Duoview source ↗
-
• twitter 21h positiveNobody is doing launch films like us https://t.co/k4z41t6wya Nobody is doing launch films like us https://t.co/k4z41t6wyaview source ↗
-
• twitter 21h positive🔥 OCTOBER 2026 SEO SAVINGS: GET 4 MONTHS FREE Get 33% OFF our Full-Service SEO Package. Sign up NOW and get a FREE month when you buy a bundle: 🌶️ 3 months → 1 month FREE 💰 6 months → 2 months FREE 🔥 9 months → 3 months FREE 🐻 12 months → 4 months FREE Book a free strategy session here: https://t.co/wRv8ROcoTP t… 🔥 OCTOBER 2026 SEO SAVINGS: GET 4 MONTHS FREE Get 33% OFF our Full-Service SEO Package. Sign up NOW and get a FREE month when you buy a bundle: 🌶️ 3 months → 1 month FREE 💰 6 months → 2 months FREE 🔥 9 months → 3 months FREE 🐻 12 months → 4 months FREE Book a free strategy session here: https://t.co/wRv8ROcoTP to get started. Lock in a full year of our comprehensive link-building service at 33% off. This isn’t just a few links. It’s the whole enchilada. A dedicated account manager, weekly strategy calls, and a custom link-building plan proven to deliver 7-figure results. Imagine THE SEO A-team bolted into your business, driving revenue without you lifting a finger. Book a free strategy session here: https://t.co/wRv8ROcoTP to get started.view source ↗
-
• twitter 21h positiveheck yeah!! I rarely ask for favors, but if you're thinking of buying a copy of my new book, I'd appreciate if you did it this week! Would be sick to get both of my books to #1 😊 https://t.co/8zyVWtLzaX heck yeah!! I rarely ask for favors, but if you're thinking of buying a copy of my new book, I'd appreciate if you did it this week! Would be sick to get both of my books to #1 😊 https://t.co/8zyVWtLzaXview source ↗
-
• twitter 21h positiveI see the word “moat” everywhere now, suddenly. Is this a trend created by AI? I swear this was not a commonly used word until like a year ago, and now everyone is using it in every possible context. Or am I manifesting some kind of linguistic synchronicity? I see the word “moat” everywhere now, suddenly. Is this a trend created by AI? I swear this was not a commonly used word until like a year ago, and now everyone is using it in every possible context. Or am I manifesting some kind of linguistic synchronicity?view source ↗
-
• twitter 21h positivehere's how you can setup one proxy for claude code, chatgpt and other ai agents basically the idea is to be able to use any model with any harness you like :) my fav part is to use multiple claude/codex subscriptions at the same time, so easily https://t.co/In1xV0RWfP here's how you can setup one proxy for claude code, chatgpt and other ai agents basically the idea is to be able to use any model with any harness you like :) my fav part is to use multiple claude/codex subscriptions at the same time, so easily https://t.co/In1xV0RWfPview source ↗
-
• twitter 22h positive🙌 So proud of this one!! Hectic race, but we handled it well. An incredible job from the everyone in the team 👏 https://t.co/EHru9F2E3w 🙌 So proud of this one!! Hectic race, but we handled it well. An incredible job from the everyone in the team 👏 https://t.co/EHru9F2E3wview source ↗
-
• twitter 22h positiveThe web is full of great apps, but most of them are just links. Introducing https://t.co/cJm8kWlrbM, an app store for the web A place to find great web apps worth using, from useful tools and new launches to the hidden gems you’d probably never find otherwise. https://t.co/lPDO1dLuQv The web is full of great apps, but most of them are just links. Introducing https://t.co/cJm8kWlrbM, an app store for the web A place to find great web apps worth using, from useful tools and new launches to the hidden gems you’d probably never find otherwise. https://t.co/lPDO1dLuQvview source ↗