September 24, 2026
51 original posts · author attribution and direct source links
OpenAI Developers
@OpenAIDevsGPT-6 Astra helps @harvey turn stacks of documents into structured legal drafts, so lawyers can focus more on strategy. https://t.co/Cm283IUzet
♡ 606 likes↻ 37 reposts↳ 71 replies
Rive
@rive_appLet's get SPOOKY 🎃 The Rive Halloween Challenge is live... Haunted UI, creepy characters, eerie shaders, ghostly games. Use the new CLI, GPU Canvas, or both. $10K in prizes. https://t.co/tOBWCoAn7H
♡ 97 likes↻ 20 reposts↳ 13 replies
Fluixo
@fluixoohttps://t.co/66ag0Vy2Qu
♡ 36 likes↻ 0 reposts↳ 10 replies
Jonny Burger
@JNYBGRThe most beautiful aesthetic right now is "it doesn’t look AI generated"
♡ 76 likes↻ 2 reposts↳ 15 replies
AI at Meta
@AIatMeta@finkd just unveiled Muse Realtime Avatar, our real-time embodiment technology that turns Muse Realtime Voice into expressive, interactive avatars. Muse Realtime Avatar enables an entirely new range of interactions in @Muse, starting with real-time conversations. 🧵👇 #MetaConnect
♡ 474 likes↻ 56 reposts↳ 73 replies
Simon Willison
@simonwI just had a voice conversation with the Datasette backup of my blog via datasette-mcp, which you can now talk to using the ChatGPT iPhone app
♡ 162 likes↻ 12 reposts↳ 105 replies
LangChain
@LangChainAnd that’s a wrap on Interrupt NYC. See you in London! https://t.co/Bh7VNhyXkf
♡ 23 likes↻ 1 reposts↳ 6 replies
Visual Studio Code
@code🚀 From our VS Code Learn library: Extending Agents! In this E2E tutorial, we'll explore key aspects of AI Agents with Tools, Tool sets, Permissions and Sandboxing. We'll also look at MCP (Model Context Protocol) and how to use it to connect your agents to external data sources. Check it out ▶️ https://t.co/L4T3cpW8kF
♡ 148 likes↻ 16 reposts↳ 14 replies
LangChain
@LangChainThe talks may be over, but the Interrupt Reception sponsored by @tavilyai has just begun! https://t.co/8TheQp5ReJ
♡ 19 likes↻ 2 reposts↳ 4 replies
LangChain
@LangChainFinal sessions of Interrupt NYC 🎙️ Fireside Chat w/ @RogoAI CEO & Co-Founder @gabestengel 🎙️ Evaluating Agentic AI at Scale with @linkedin https://t.co/kLEMO6bftf
♡ 13 likes↻ 1 reposts↳ 5 replies
LangChain
@LangChainBefore Interrupt wraps up, stop by the LangChain Agent Arena! 🕹️ Play 30 seconds of Tetris to train your style 👉 Choose the model that plays it for you 👀 Watch it battle the reigning champion https://t.co/tSVU2zvcCz
♡ 11 likes↻ 0 reposts↳ 4 replies
LangChain
@LangChainA few things you can build: 1️⃣ Annotation queues: Review and label one (or many) runs at a time 2️⃣ Experiment comparisons: Compare outputs and metrics across experiments side by side 3️⃣ Trace reviews: Build trace or thread history views to inspect app behavior https://t.co/FlkGPcfsHV
♡ 30 likes↻ 2 reposts↳ 6 replies
LangChain
@LangChainAnother awesome feature in Managed Deep Agents 0.8
♡ 24 likes↻ 0 reposts↳ 1 replies
LangChain
@LangChainManaged Deep Agents 0.8 makes the Slack experience even better!
♡ 18 likes↻ 0 reposts↳ 2 replies
LangChain
@LangChainIntroducing LangSmith Custom Apps Create any interface from your agent data with a prompt. If you can think it, LangSmith can build it. Now GA. https://t.co/MayBpUbPdu https://t.co/9AODngofKx
♡ 72 likes↻ 8 reposts↳ 10 replies
LlamaIndex 🦙
@llama_indexconfidence scores only matter if they help you decide what to automate. for document extraction, that usually means knowing how much work you can safely accept at a given precision target. in our latest post, we look at confidence scoring through that lens, including: ✅️ confidence cutoffs ✅️ precision vs. recall ✅️ score coverage ✅️ score granularity ✅️ human review volume using ExtractBench, we compare how different extraction systems perform after confidence filtering. at a 97% precision target, LlamaParse Agentic Plus reached 66.48% recall on expected fields after filtering. the useful part of a confidence score isn’t the number itself. it’s whether you can use it to control automation and review in production. 👉️ read the full post: https://t.co/U462MW2JOf
♡ 24 likes↻ 6 reposts↳ 7 replies
LangChain
@LangChainUp next at Interrupt 🎙️ Fireside Chat w/ @OpenRouter CEO & Co-Founder @alexatallah 🎙️ Building Engine: How we approach agent improvement w/ @bentannyhill https://t.co/0u7XviPsOJ
♡ 8 likes↻ 2 reposts↳ 4 replies
LangChain
@LangChainInterrupt NYC Swag spotlight: ⌨️ A clicky fidget keycap ❄️ LangChain Sweatshirt 🖊️ Pens https://t.co/iEZPrgo5gV
♡ 32 likes↻ 0 reposts↳ 2 replies
Framer
@framerLearn how positioning in Framer works by understanding what each layer is measured against. 00:00 Four positioning modes 00:41 Relative positioning 01:47 Absolute positioning 02:33 Fixed positioning 03:01 Sticky positioning 03:27 Recap https://t.co/l7qKNTBW88
♡ 58 likes↻ 5 reposts↳ 6 replies
LangChain
@LangChainThe LangSmith Engine that could (be won) https://t.co/RENVfRAGO5
♡ 17 likes↻ 0 reposts↳ 0 replies
LangChain
@LangChainIntroducing LangSmith Fine-Tuning and the smithtune CLI. LangSmith now handles the entire fine-tuning process. Use your traces to train specialized models that cut cost and latency. Now in Public Beta. https://t.co/hhH5Tvlm7e
♡ 97 likes↻ 13 reposts↳ 13 replies
LangChain
@LangChain1️⃣ Identify + export trajectories from LangSmith 2️⃣ Transform traces into SFT-ready training examples 3️⃣ Fine-tune open models w/ @baseten + @fireworks_AI 4️⃣ Evaluate in LangSmith All in one simple workflow. https://t.co/mbDEs4eT6z
♡ 9 likes↻ 1 reposts↳ 1 replies
LangChain
@LangChainWhat is a trajectory? A conversational view of an agent session that pulls together: ✅ Human messages ✅ AI messages ✅ Tool messages ✅ System prompts …across the main agent + any subagents, then shows them in the order they first appeared.
♡ 48 likes↻ 5 reposts↳ 6 replies
LangChain
@LangChainAfter lunch, here’s what’s up next at Interrupt: 🎙️How @airbnb built Agentic AI on LangGraph 🎙️Deploying mission-critical agents to production w/ @VictorMoreira16 🎙️LangSmith for Mental Health AI w/ @SpringHealth https://t.co/ymkqOQrvYk
♡ 21 likes↻ 2 reposts↳ 4 replies
LangChain
@LangChainIntroducing Trajectories in LangSmith. A view of agent behavior that everyone on the team can understand at a glance. https://t.co/8s9kHol2LO https://t.co/8cGrmhVa2F
♡ 133 likes↻ 11 reposts↳ 12 replies
Rive
@rive_appRead the full rules here 👇 https://t.co/mL4wHtRDsJ
♡ 9 likes↻ 1 reposts↳ 0 replies
GitHub
@githubDependabot pull requests are easy to review one at a time ... and tedious to review by the dozen. Build a GitHub Copilot app automation that does the first pass for you. Once it reviews open Dependabot pull requests, groups them by risk, verifies CI status, it'll provide a short summary. You write the instructions in plain language, so you can shape the automation to match how your team works. Schedule it before your workday starts and the results are ready when you log in. Try it out 👇 https://t.co/d83HeLTV7h
♡ 147 likes↻ 16 reposts↳ 46 replies
LangChain
@LangChainSpecial guests at the LangChain Demo Station: @nvidia! Stop by and say hello during lunch! https://t.co/lAhK1gQSXp
♡ 7 likes↻ 0 reposts↳ 2 replies
LangChain
@LangChainAnd it’s time for a break! Grab lunch before we kick off the next round of sessions + workshops! https://t.co/P5oPCJ14UM
♡ 12 likes↻ 0 reposts↳ 1 replies
LangChain
@LangChainIntroducing Managed Deep Agents 0.8 ✅ User-owned credentials + memory let agents work off correct permissions & user-specific context. ✅ HTTP channels for bringing agents into internal tools ✅ Native @slackhq file transfers ✅ Built-in web search via @p0
♡ 57 likes↻ 12 reposts↳ 13 replies
LangChain
@LangChainAt Interrupt? 🕹️ Try your hand at Agent Claw 🚂 Play for a LangSmith Engine https://t.co/Os10m96ktZ
♡ 14 likes↻ 2 reposts↳ 3 replies
LangChain
@LangChainNew in v2: ✅ Red Teaming: Engine identifies issues in your agent before they surface in production ✅ Validated Fixes: Engine tests its proposed fixes to confirm they work before showing them to users ✅ Improved Issue Identification: Engine now surfaces inefficient agent work and trends in key metrics like cost and latency
♡ 58 likes↻ 7 reposts↳ 7 replies
LangChain
@LangChainNext on the Interrupt main stage: 🎙️Building Jarvis: @jpmorgan’s Agent Building Assembly Line 🎙️How @useapolloio rearchitected a production GTM assistant w/ Deep Agents 🎙️Scaling Custom Agentic AI Across @Omnicom w/ @webershandwick + @focused_dot_io https://t.co/FhtAMfgkXM
♡ 8 likes↻ 0 reposts↳ 2 replies
LangChain
@LangChainJust announced at Interrupt: LangSmith Engine v2. With Engine v2, you can proactively spot agent issues and resolve them before your users see them. Your agents get better. You get back to building. https://t.co/qCV4PV7C5l https://t.co/1DF66hoV1v
♡ 54 likes↻ 9 reposts↳ 8 replies
LangChain
@LangChainHappening now: @modal Fireside Chat w/ CEO + Co-Founder @bernhardsson https://t.co/ajl2okw6FK
♡ 15 likes↻ 0 reposts↳ 2 replies
LangChain
@LangChainIn case you missed @hwchase17’s Interrupt Keynote: ✅ LangSmith Engine v2 ✅ Managed Deep Agents 0.8 ✅ LangSmith Trajectories ✅ LangSmith Fine-Tuning ✅ Custom Apps https://t.co/lt2o5IKIc7 https://t.co/eWzmnxJcS2
♡ 27 likes↻ 3 reposts↳ 3 replies
School of Motion
@SchoolOfMotionIf you still think of Canva as just a tool for making quick social media graphics, their new ProSuite announcement just might change your mind! Find out more on Motion Mondays! ➡️ https://t.co/2WMvGwbh9y https://t.co/VGppIuSYQ0
♡ 3 likes↻ 0 reposts↳ 2 replies
Visual Studio Code
@codeAccessibility is more than making a product usable. It’s about helping every developer thrive. 🎬 The Story of VS Code: https://t.co/Q7cZIVj0d0 #vscode #storyofvscode https://t.co/QZA7ddBsCq
♡ 71 likes↻ 3 reposts↳ 2 replies
LangChain
@LangChainPacked house for @hwchase17’s opening keynote! https://t.co/vZvof0CEIC
♡ 29 likes↻ 2 reposts↳ 2 replies
LangChain
@LangChainJoin the opening keynote livestream: https://t.co/SNB4bvlcpe https://t.co/LIozexLwJw
♡ 11 likes↻ 2 reposts↳ 1 replies
Visual Studio Code
@code✨ One model. Three ways to edit your code. The new 3-in-1 Inline Suggestions model brings completions, Next Edit Suggestions, and longer-distance edits together in one model. 📖 Learn how we built it: https://t.co/GGeD2554DC Happy coding! 💙
♡ 168 likes↻ 15 reposts↳ 14 replies
LangChain
@LangChain🔴 Going live in 15!!!
♡ 6 likes↻ 0 reposts↳ 0 replies
LangChain
@LangChainIt wouldn’t be an agent conference without humans in the loop. https://t.co/QSVkWZa7wt
♡ 29 likes↻ 3 reposts↳ 6 replies
LangChain
@LangChainAt Interrupt? Grab some breakfast + coffee from our sponsors at @focused_dot_io + @FactoryAI before we kick off! https://t.co/LtTldx4DYC
♡ 8 likes↻ 1 reposts↳ 1 replies
LangChain
@LangChainWant to see what’s next for agents? We’re livestreaming @hwchase17’s keynote at 9:30AM ET! https://t.co/SNB4bvkEzG
♡ 15 likes↻ 2 reposts↳ 1 replies
GitHub
@githubMore #GitHubUniverse sessions just dropped 🆕 Grab your pass, and we'll see you October 28-29 🌁 https://t.co/P78J1QQHjA https://t.co/b8pQGJleWS
♡ 65 likes↻ 5 reposts↳ 3 replies
GSAP
@greensock💚 Site of the Day - Mathilde De Chiara • Portfolio by Guignand Thibault ⚙️ ScrollTrigger, SplitText, CustomEase, ScrollTo 🛠️ Reduced Motion, SVG, React, Web GL, OGL, Lenis, GLSL, TypeScript, Vite, Sanity site → https://t.co/hQVd3LKRo2 showcase → https://t.co/zGjV9MynPN https://t.co/TPEOGDsPXq
♡ 40 likes↻ 0 reposts↳ 2 replies
AI at Meta
@AIatMetaWe put Muse Realtime Avatar head-to-head with two leading commercial avatar systems in their own live-call products. Raters held 2–3 minute conversations with matched avatar identities, then compared visual quality, sync, character consistency, and mannerisms. Muse Realtime Avatar came out ahead on overall preference.
♡ 24 likes↻ 3 reposts↳ 7 replies
AI at Meta
@AIatMetaRead our research blog to learn more about Muse Realtime Avatar: https://t.co/pVq9K0fxCG
♡ 21 likes↻ 2 reposts↳ 4 replies
swyx
@swyxbenched
♡ 8 likes↻ 0 reposts↳ 9 replies




















