•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 3426–3450 of 4998 mentions
-
• twitter 1w positiveagent is like "i don't have an environment to run this in" thankfully, we have /figure-it-out thanks @poteto agent is like "i don't have an environment to run this in" thankfully, we have /figure-it-out thanks @potetoview source ↗
-
• twitter 1w positiveBuilding agent workflows from scratch gets messy fast. This repo gives you reusable building blocks. Skills is a personal library of domain-agnostic AI agent skills for builders creating software factories with skill-compatible harnesses. It helps you move from an idea to a reviewable implementation by combining expl… Building agent workflows from scratch gets messy fast. This repo gives you reusable building blocks. Skills is a personal library of domain-agnostic AI agent skills for builders creating software factories with skill-compatible harnesses. It helps you move from an idea to a reviewable implementation by combining exploration, specification, implementation, review, and research skills that can run as a pipeline or individually. Key features: • Cross-harness install – add the library with `npx skills add dzhng/skills` or copy individual skill folders into a harness • End-to-end feature loop – map unknowns, write a spec, implement it, and review the resulting choices • Independent skill modules – use a chained pipeline for a feature or pick a single skill when that is all you need • Research workflow – run fast experiments with baselines, evaluation targets, and a parameter-effect map • Review coverage – includes code review, test auditing, documentation, and visual-review skills It’s open-source (MIT license). Link in the reply 👇view source ↗
-
• twitter 1w positiveLuke really said "Hermes should be an OPERATING SYSTEM." 🪽 And then... ...he just started building it. 🤯 We are living through the most amazing time in human history right now. 👇 Luke really said "Hermes should be an OPERATING SYSTEM." 🪽 And then... ...he just started building it. 🤯 We are living through the most amazing time in human history right now. 👇view source ↗
-
• twitter 1w positiveMost people will scroll past this Claude Code update. That's a mistake. Mods aren't a cosmetic tweak. They're Anthropic handing you the keys. Here's why this is a real jump: Hooks (before): → React to a few events as they happen → Watch, but can't change much Mods (now): ✔ Rewrite a prompt before it reaches th… Most people will scroll past this Claude Code update. That's a mistake. Mods aren't a cosmetic tweak. They're Anthropic handing you the keys. Here's why this is a real jump: Hooks (before): → React to a few events as they happen → Watch, but can't change much Mods (now): ✔ Rewrite a prompt before it reaches the model ✔ Draw brand-new panels on your screen ✔ Swap out built-in features entirely Anthropic even turned some of its own features, like the diff view, into mods you can switch off or replace. And they've said more built-in features are moving to mods over time. My take: the people who learn this early will have a setup that fits like a glove. Everyone else keeps running the plain version out of the box. One tip from my own testing: build mods with Opus 5.5. It felt noticeably smarter than Sonnet 5.5 at getting the code right the first time. 🧠 Save this video, you'll thank yourself when your setup is fully custom. Want the SOP? DM me.view source ↗
-
• twitter 1w positiveHooks were step one. Mods are the real upgrade. Here's why this matters more than it looks. 🔥 Claude Code already had hooks. They let you react to certain moments as they happened. But hooks couldn't: ✔ Rewrite what was happening ✔ Draw new things on your screen ✔ Replace an existing feature Mods do all three. … Hooks were step one. Mods are the real upgrade. Here's why this matters more than it looks. 🔥 Claude Code already had hooks. They let you react to certain moments as they happened. But hooks couldn't: ✔ Rewrite what was happening ✔ Draw new things on your screen ✔ Replace an existing feature Mods do all three. A mod doesn't just watch. It steps in before, after, or instead of an action. What that unlocks: → Scrub messy output before Claude sees it → Hide private keys automatically → Pause a command to ask you first → Re-run a command a smarter way → Change the color theme or layout Julian reports that 2 mods he asked for were ready in about 60 seconds, without writing a single line of code. My take: the people who customise early will have a setup built around how they work. Save this video, you'll see why this is a bigger shift than it seems. Want the SOP? DM me.view source ↗
-
• twitter 1w positiveIdeally, I would have been in Prague today, but the Indian visa process really slaps you hard I got selected as a speaker at ValkeyConf in Prague, which is happening today, but sadly my visa didn’t make it through in time EU tour slipped and Asia tour continues i guess! :) Though, really thanks to the ValkeyConf tea… Ideally, I would have been in Prague today, but the Indian visa process really slaps you hard I got selected as a speaker at ValkeyConf in Prague, which is happening today, but sadly my visa didn’t make it through in time EU tour slipped and Asia tour continues i guess! :) Though, really thanks to the ValkeyConf team for considering me and for all the help they provided throughout. Really appreciate it. What’s next? I am going to slow down on travelling for a bit (~2months). I have covered close to 8–9 countries in just a year and it’s been incredibly fun I want to just drill myself down and try to experiment + research more instead. I am not very positive about this because I usually end up being more productive while travelling rather than staying home, which is oddly surprising because travels are usually meant for holidays? But there’s no sense of schedule while travelling. Weird sleep cycles, no proper health activities, inconsistent food, and basically no routine. Anyways, if it doesn’t fit me, I will get back to travelling hehe What recently? → I was at KCD Gujarat as a speaker!! Will rant about it in a new post. → I built an indie game last weekend! It’s here, go try it out: Moonlit Grid https://t.co/TOZ5T8YL3Hview source ↗
-
• twitter 1w positiveDesign sites I keep coming back to. - https://t.co/yOIV4w1shW - https://t.co/l6oOlUW6bf - https://t.co/A4iveG8emy - https://t.co/msV8CUEPaQ - https://t.co/CQ48cWbFVb - https://t.co/uLagQVVqaz Real sites and real UI. Better than an hour of Dribbble. https://t.co/KlbTWsvAm6 Design sites I keep coming back to. - https://t.co/yOIV4w1shW - https://t.co/l6oOlUW6bf - https://t.co/A4iveG8emy - https://t.co/msV8CUEPaQ - https://t.co/CQ48cWbFVb - https://t.co/uLagQVVqaz Real sites and real UI. Better than an hour of Dribbble. https://t.co/KlbTWsvAm6view source ↗
-
• twitter 1w positiveWhat do 10X fast developers do? What do 10X fast developers do?view source ↗
-
• twitter 1w positiveAccept setbacks as part of a life that is still worth living well. Accept setbacks as part of a life that is still worth living well.view source ↗
-
• twitter 1w positiveSave time, make money and get customers with FREE AI → https://t.co/2rK7SLQfZK https://t.co/PVDxHau8wL Save time, make money and get customers with FREE AI → https://t.co/2rK7SLQfZK https://t.co/PVDxHau8wLview source ↗
-
• twitter 1w positiveHi @theo, I’m a firmware engineer with experience working on kernels, boot code, drivers in C/assembly, etc. I also built my own agent orchestration and context management tooling. Low-level OS work + agents is exactly my kind of project. I’d love to help making it not the worst OS ever. Hi @theo, I’m a firmware engineer with experience working on kernels, boot code, drivers in C/assembly, etc. I also built my own agent orchestration and context management tooling. Low-level OS work + agents is exactly my kind of project. I’d love to help making it not the worst OS ever.view source ↗
-
• twitter 1w positiveHerald OS remembers my unfinished projects better than I do That website I left halfway through. The draft I was “definitely finishing tomorrow.” I open it and Hermes catches me up on where I stopped. One click and it carries on. No digging through tabs. No explaining the whole project again. And it asks before ch… Herald OS remembers my unfinished projects better than I do That website I left halfway through. The draft I was “definitely finishing tomorrow.” I open it and Hermes catches me up on where I stopped. One click and it carries on. No digging through tabs. No explaining the whole project again. And it asks before changing anything. I’m still in control. Built on Hermes Agent. Going Open Source soon! https://t.co/9GinU8YqS3view source ↗
-
• twitter 1w positiveThe biggest open source program of this month has already started. You can get an iPhone Duo, a MacBook Pro and cash prizes for contributing to open source this month. If you're already contributing for Hacktoberfest this month, we're bringing Mergetober alongside it, a more focused program with some incredible pri… The biggest open source program of this month has already started. You can get an iPhone Duo, a MacBook Pro and cash prizes for contributing to open source this month. If you're already contributing for Hacktoberfest this month, we're bringing Mergetober alongside it, a more focused program with some incredible prizes. The challenge is to build integrations for @cognee_, the open source memory layer for AI agents. Pick an open issue or propose a new integration, get assigned, open a PR before October 31, and you're in. The features you add will be used by developers and companies around the world. All the details: https://t.co/2gAyX6guHsview source ↗
-
• twitter 1w positive这拿去抖音不是分分钟起号了？😍 太自然了～ 提示词见评论👇 https://t.co/HElgoFV7kd 这拿去抖音不是分分钟起号了？😍 太自然了～ 提示词见评论👇 https://t.co/HElgoFV7kdview source ↗
-
• twitter 1w positiveYour SEO Should Work Harder Than Your Coffee Does Digital entrepreneurs, your rankings should grow while you sleep. https://t.co/wRv8ROcoTP That pace reaches 118,625 clicks across twelve months. Our free session reveals where your biggest opportunities hide. Prices increase soon, so waiting could cost you more. O… Your SEO Should Work Harder Than Your Coffee Does Digital entrepreneurs, your rankings should grow while you sleep. https://t.co/wRv8ROcoTP That pace reaches 118,625 clicks across twelve months. Our free session reveals where your biggest opportunities hide. Prices increase soon, so waiting could cost you more. Only a few spots remain for serious digital entrepreneurs. ✅ Get a custom strategy built around your business. ✅ Discover premium backlink opportunities available for stronger authority. ✅ Stronger rankings need authority signals competitors cannot easily copy. ✅ Spot hidden keyword opportunities before competitors grab them. ✅ Paid services include a fourteen day money back guarantee. ✅ Sign up now before you miss out completely. https://t.co/wRv8ROcoTPview source ↗
-
• twitter 1w positiveworking on myself because it wasn't my fault, but it IS my responsibility to heal and make sure that it doesn't control me for the rest of my life. working on myself because it wasn't my fault, but it IS my responsibility to heal and make sure that it doesn't control me for the rest of my life.view source ↗
-
• twitter 1w positiveanybody have a dataset of 1-10k of the most beautiful landing pages on the planet? anybody have a dataset of 1-10k of the most beautiful landing pages on the planet?view source ↗
-
• twitter 1w positiveThe best SEO tool in the world: https://t.co/qngRyc06ii The best SEO tool in the world: https://t.co/qngRyc06iiview source ↗
-
• twitter 1w positiveThis YouTube channel didn't exist 24 hours ago... With only 5 videos, it has 8.3K monetized views (which made me $70) Comment "Guide" under this tweet and I'll send you a FREE document Explaining how you can do it too (Must be following so I can DM) https://t.co/5EdWqdzxAY This YouTube channel didn't exist 24 hours ago... With only 5 videos, it has 8.3K monetized views (which made me $70) Comment "Guide" under this tweet and I'll send you a FREE document Explaining how you can do it too (Must be following so I can DM) https://t.co/5EdWqdzxAYview source ↗
-
• twitter 1w positiveA new AI model just topped real-world coding benchmarks. Not a rumor, not a leak. Google announced it. Meet Gemini 4 Argon, released September 30, 2026. 🚀 It's built for "long-horizon workflows": tasks with lots of steps, lots of thinking, and lots of back-and-forth. → 77.9% on DeepSWE v1.1, a new state of the art… A new AI model just topped real-world coding benchmarks. Not a rumor, not a leak. Google announced it. Meet Gemini 4 Argon, released September 30, 2026. 🚀 It's built for "long-horizon workflows": tasks with lots of steps, lots of thinking, and lots of back-and-forth. → 77.9% on DeepSWE v1.1, a new state of the art for real-world software engineering → Up to 1M output tokens in one response (it was 64K before) → Multimodal reasoning across charts, videos, and documents → Agentic, so it can run code and take actions, not just answer questions Google thousands of employees are already using it for coding, deep research, and document writing. Save this video, you'll know exactly why this launch matters before your feed explains it for you. Want the SOP? DM me.view source ↗
-
• twitter 1w positive30 things that will get you hired as an AI engineer in 2026: – Ship one agent real people use every week – Know when NOT to use an LLM – Write evals before writing prompts – Build an MCP server from scratch – Connect an agent to 5+ real tools – Design memory that forgets the right things – Pick the cheapest mod… 30 things that will get you hired as an AI engineer in 2026: – Ship one agent real people use every week – Know when NOT to use an LLM – Write evals before writing prompts – Build an MCP server from scratch – Connect an agent to 5+ real tools – Design memory that forgets the right things – Pick the cheapest model that passes your evals – Route easy tasks to small models, hard ones to big ones – Cut your inference bill in half and show the numbers – Cache repeat answers so they cost almost nothing – Make long workflows resume after a crash – Validate every model output against a schema – Sandbox every tool call – Defend against prompt injection from docs and web pages – Keep secrets and PII out of the context window – Add human approval before risky actions – Trace every model call and tool call – Debug a failing agent from its logs alone – Grade the agent's steps, not just its final answer – Turn real user failures into test cases – Block deploys when eval scores drop – Test new models on a slice of real traffic first – Add a fallback when your model provider goes down – Stream responses so users never wait on a spinner – Fine-tune a small model on your best outputs – Version prompts like code – Measure cost and latency per task – Write a README anyone understands in 5 minutes – Record a 60-second demo that shows it working – Post what broke and how you fixed it Nobody asks for your certificate. They ask "what did you ship?" Bookmark this + send it to someone prepping for AI interviews.view source ↗
-
• twitter 1w positiveRT @dabit3: strong people lift others up. weak people pull others down. winners focus on winning. losers focus on winners. people doing gre… RT @dabit3: strong people lift others up. weak people pull others down. winners focus on winning. losers focus on winners. people doing gre…view source ↗
-
• twitter 1w positiveWow this is amazing 🔥 Google is now including Colab inside their Gemini plans... so you have access to premium GPUs!! You can basically: - Run any open source model - Even image/audio/video gen - Fine-tune a lot of OSS models Everything on an expensive Nvidia GPU without having to rent it or own it. So many possibi… Wow this is amazing 🔥 Google is now including Colab inside their Gemini plans... so you have access to premium GPUs!! You can basically: - Run any open source model - Even image/audio/video gen - Fine-tune a lot of OSS models Everything on an expensive Nvidia GPU without having to rent it or own it. So many possibilities. Time to build!view source ↗
-
• twitter 1w positive@maria_rcks My experience with grok in my Tesla could be much better as well lol @maria_rcks My experience with grok in my Tesla could be much better as well lolview source ↗
-
• twitter 1w positiveToday is National Be Nice Day. Today is National Be Nice Day.view source ↗