•twitter5573
listening to
timeline
5573
mentions
tracked
tracked
net sentiment
+24%
1767 positive
3384 neutral
422 negative
volume & sentiment over time
Sep 30 – Oct 5, 2026 · Daily
sources
most discussed
—
active days
6
mentions
Showing 1901–1925 of 5573 mentions
-
• twitter 1d neutralالرئيس العليمي: أعلن بدء العمليات العسكرية لاستعادة ما تبقى من أراضي البلاد #العربية_عاجل الرئيس العليمي: أعلن بدء العمليات العسكرية لاستعادة ما تبقى من أراضي البلاد #العربية_عاجلview source ↗
-
• twitter 1d neutralAI agents can read websites, but WebMCP can let them use website tools directly. In this guide, @chudinnorukam explains how (and why) he shipped WebMCP on two live sites despite near-zero adoption today. You'll learn how to expose read-only tools through SvelteKit and Next.js and prepare your site for agent interacti… AI agents can read websites, but WebMCP can let them use website tools directly. In this guide, @chudinnorukam explains how (and why) he shipped WebMCP on two live sites despite near-zero adoption today. You'll learn how to expose read-only tools through SvelteKit and Next.js and prepare your site for agent interactions. https://t.co/mP63wsnW3Eview source ↗
-
• twitter 1d neutralHi I’m Eshaan. This is what I am building at 22. Let’s connect. https://t.co/wfbluqge46 Hi I’m Eshaan. This is what I am building at 22. Let’s connect. https://t.co/wfbluqge46view source ↗
-
• twitter 1d positiveDay 9 of 100 Days of AI 🤖 I’m nice to AI for strategic reasons. https://t.co/08BDtkkdpB Day 9 of 100 Days of AI 🤖 I’m nice to AI for strategic reasons. https://t.co/08BDtkkdpBview source ↗
-
• twitter 1d positive🤖 archify ⭐ 76,933 stars Stop manually drawing system architecture. Turn any codebase, plan, or complex idea into a beautiful interactive diagram instantly. 🔗 https://t.co/5MJ5UScteP #AI #MachineLearning https://t.co/URult4Cvx0 🤖 archify ⭐ 76,933 stars Stop manually drawing system architecture. Turn any codebase, plan, or complex idea into a beautiful interactive diagram instantly. 🔗 https://t.co/5MJ5UScteP #AI #MachineLearning https://t.co/URult4Cvx0view source ↗
-
• twitter 1d positive🐐 OTD in 2008, Messi scored his first-ever free-kick goal https://t.co/nNf403R9W9 🐐 OTD in 2008, Messi scored his first-ever free-kick goal https://t.co/nNf403R9W9view source ↗
-
• twitter 1d neutralMost people don't need more motivation. They need to stop negotiating with the version of themselves that keeps choosing comfort. How many years have you lost waiting to feel ready? Most people don't need more motivation. They need to stop negotiating with the version of themselves that keeps choosing comfort. How many years have you lost waiting to feel ready?view source ↗
-
• twitter 1d positiveYour idea doesn't need to be perfect. It needs to exist. Your idea doesn't need to be perfect. It needs to exist.view source ↗
-
• twitter 1d neutralhttps://t.co/i64LRttgiR https://t.co/i64LRttgiRview source ↗
-
• twitter 1d neutralWhere do you usually learn a new Hermes trick first? Docs, X, Discord, YouTube, /help, somewhere else? Where do you usually learn a new Hermes trick first? Docs, X, Discord, YouTube, /help, somewhere else?view source ↗
-
• twitter 1d neutralAs an AI Evals Engineer, you must build these projects. 1.) Trajectory Grading Engine Build: Step-level evaluator that scores agent tool calls against a deterministic DAG, failing the run if it hallucinates an API parameter or skips a safety check. Why: Final-answer evals hide the exact step where agents break. The… As an AI Evals Engineer, you must build these projects. 1.) Trajectory Grading Engine Build: Step-level evaluator that scores agent tool calls against a deterministic DAG, failing the run if it hallucinates an API parameter or skips a safety check. Why: Final-answer evals hide the exact step where agents break. The trajectory is the unit of accountability. 2.) Shadow Routing Comparator Build: Proxy that mirrors 5% of prod traffic to a new model, diffs the trajectories and auto-generates a cost/quality report without affecting users. Why: You cannot A/B test non-determinism safely without shadow mode. 3.) Calibrated LLM-as-a-Judge Build: Evaluation pipeline that measures the judge's verbosity, position and self-preference biases against 500 human-labeled anchors. Why: Uncalibrated judges are just expensive vibes. Calibrated judges are scientific instruments. 4.) CI/CD Regression Gate Build: GitHub Action that runs parameterized evals on every PR and blocks merges if task success drops >2% or latency spikes. Why: Evals that do not block deploys are just dashboards not gates. 5.) RAG Adversarial Harness Build: Test suite injecting irrelevant context, missing citations and contradictory documents to force the model to confidently abstain. Why: RAG's biggest risk isn't a bad answer... it's a confident, ungrounded lie. 6.) Automated DPO Flywheel Build: Pipeline capturing user thumbs-downs, auto-formatting them into preference pairs and triggering a nightly LoRA fine-tune. Why: Your production edge cases are the highest-leverage training data you own. 7.) Statistical Significance Engine Build: Bootstrapping utility that outputs "Model B wins by 3.2% ± 1.1% (p<0.05)" instead of raw accuracy scores. Why: A 2-point delta on 50 samples is noise. Executives make million-dollar routing decisions on your math. 8.) Agent Red-Team Fuzzer Build: Automated harness that injects prompt injections, malformed tool schemas and infinite loops into agent inputsview source ↗
-
• twitter 1d positiveAfter months of work, I can proudly say that Grids is going to release this month! 🤩 https://t.co/kRpfqk3QaL After months of work, I can proudly say that Grids is going to release this month! 🤩 https://t.co/kRpfqk3QaLview source ↗
-
• twitter 1d positivewhoever leaked this is f*cking crazy someone mapped 300+ AI agents into one GitHub repo - and basically leaked the shortlist of what’s actually worth trying. coding agents. browser agents. memory. voice. research. multi-agent teams. local models. sandboxes. evals. all sitting on one page. and once you start openin… whoever leaked this is f*cking crazy someone mapped 300+ AI agents into one GitHub repo - and basically leaked the shortlist of what’s actually worth trying. coding agents. browser agents. memory. voice. research. multi-agent teams. local models. sandboxes. evals. all sitting on one page. and once you start opening the categories, you realize how much stuff people are still building from scratch for absolutely no reason. want an AI that works inside your codebase? -> Aider / Continue want agents working together like a tiny company? -> CrewAI / AutoGen / MetaGPT want your agent to actually remember you tomorrow? -> Mem0 want it running code somewhere that isn’t your laptop? -> E2B want models running locally for $0/token? -> Ollama want to see what your agent actually did after it inevitably does something weird? -> AgentOps and that’s barely scratching it. there are 300+ projects across ~25 categories. the real cheat code isn’t downloading all of them. it’s opening the repo before you build anything and asking: “has someone already solved this?” because there’s a pretty good chance the answer is yes - and the open-source version already has thousands of people testing it for you. I went through the map and pulled out the agents I’d actually start with + my pick for every major part of the stack. full 300+ AI agent list belowview source ↗
-
• twitter 1d neutral📼 https://t.co/pamte1zuOp https://t.co/JOkWrgneou 📼 https://t.co/pamte1zuOp https://t.co/JOkWrgneouview source ↗
-
• twitter 1d neutrale2e is #1 trending repo on GitHub today https://t.co/J3j1w2n9tp e2e is #1 trending repo on GitHub today https://t.co/J3j1w2n9tpview source ↗
-
• twitter 1d neutralVersus Trade is hiring: Middle UI/UX Designer Fully remote Design mobile and responsive web interfaces and landing pages for a fintech product. Develop visual concepts and complete user flows while collaborating with product and dev teams. https://t.co/T5QoT78rPj https://t.co/e6wYR7UjBD Versus Trade is hiring: Middle UI/UX Designer Fully remote Design mobile and responsive web interfaces and landing pages for a fintech product. Develop visual concepts and complete user flows while collaborating with product and dev teams. https://t.co/T5QoT78rPj https://t.co/e6wYR7UjBDview source ↗
-
• twitter 1d neutralhttps://t.co/gCGCk680B6 https://t.co/gCGCk680B6view source ↗
-
• twitter 1d positiveThe best tier list! https://t.co/YNGA2QiU2q The best tier list! https://t.co/YNGA2QiU2qview source ↗
-
• twitter 1d positiveCreate polished animations without After Effects. With Orelin, turn your designs into beautiful motion pieces in just a few clicks. Try it yourself: https://t.co/HBw7BQuzqX https://t.co/pxY4FGkqU4 Create polished animations without After Effects. With Orelin, turn your designs into beautiful motion pieces in just a few clicks. Try it yourself: https://t.co/HBw7BQuzqX https://t.co/pxY4FGkqU4view source ↗
-
• twitter 1d neutralIf users keep asking for the same thing, listen. If users keep asking for the same thing, listen.view source ↗
-
• twitter 1d negativeIf you never let people feel the consequences of how they treat you, you become a safe house for their worst behavior. They don’t change. They just learn you’re free to disrespect. If you never let people feel the consequences of how they treat you, you become a safe house for their worst behavior. They don’t change. They just learn you’re free to disrespect.view source ↗
-
• twitter 1d negativeOne insight from building a voice AI agent for macOS: When an AI feature returns invalid structured data, don’t show the raw error or silently guess. 1. Define the fields the next step actually needs. 2. Validate the response before saving or triggering an action. 3. If it fails, keep the user’s input and offer a ret… One insight from building a voice AI agent for macOS: When an AI feature returns invalid structured data, don’t show the raw error or silently guess. 1. Define the fields the next step actually needs. 2. Validate the response before saving or triggering an action. 3. If it fails, keep the user’s input and offer a retry or edit. A malformed optional field shouldn’t block a useful draft. Small UX detail. Big difference.view source ↗
-
• twitter 1d neutralWhen things go wrong, take a moment to be thankful for what’s going right. 🌞🙏 https://t.co/wcsOW551Mb When things go wrong, take a moment to be thankful for what’s going right. 🌞🙏 https://t.co/wcsOW551Mbview source ↗
-
• twitter 1d neutralLaunching Jigyasha: An AI teaching assistant that teaches you concepts by asking you questions first and intuitively helps you solve questions, and you learn the topic. Completely open source. (link in replies) https://t.co/aVILaYUSdK Launching Jigyasha: An AI teaching assistant that teaches you concepts by asking you questions first and intuitively helps you solve questions, and you learn the topic. Completely open source. (link in replies) https://t.co/aVILaYUSdKview source ↗
-
• twitter 1d neutralAny chance of a Sunday reset @AnthropicAI? 🫠🙏 https://t.co/gEbwfHpOSL Any chance of a Sunday reset @AnthropicAI? 🫠🙏 https://t.co/gEbwfHpOSLview source ↗