Original source archive

September 24, 2026

51 original posts · author attribution and direct source links

Coding & agents𝕏

more conferences could implement this. so much high value time wasted without thought https://t.co/jn93l7JyoH

Media from the original post
♡ 1.5K likes↻ 112 reposts↳ 70 replies
Collected original
View original post on X ↗
Coding & agents𝕏

GPT-6 Astra helps @harvey turn stacks of documents into structured legal drafts, so lawyers can focus more on strategy. https://t.co/Cm283IUzet

Media from the original post
♡ 606 likes↻ 37 reposts↳ 71 replies
Collected original
OpenAIv6Video
View original post on X ↗
Video & motion𝕏

Let'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

Media from the original post
♡ 97 likes↻ 20 reposts↳ 13 replies
Collected original
RiveVideo
View original post on X ↗
Models𝕏

https://t.co/66ag0Vy2Qu

♡ 36 likes↻ 0 reposts↳ 10 replies
Collected original
View original post on X ↗
Video & motion𝕏

The most beautiful aesthetic right now is "it doesn’t look AI generated"

♡ 76 likes↻ 2 reposts↳ 15 replies
Collected original
View original post on X ↗
Models𝕏

@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

Media from the original post
♡ 474 likes↻ 56 reposts↳ 73 replies
Collected original
Video
View original post on X ↗
Models𝕏

I 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
Collected original
OpenAI
View original post on X ↗
Coding & agents𝕏

And that’s a wrap on Interrupt NYC. See you in London! https://t.co/Bh7VNhyXkf

Media from the original post
♡ 23 likes↻ 1 reposts↳ 6 replies
Collected original
View original post on X ↗
Coding & agents𝕏

🚀 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

Media from the original post
♡ 148 likes↻ 16 reposts↳ 14 replies
Collected original
View original post on X ↗
Coding & agents𝕏

The talks may be over, but the Interrupt Reception sponsored by @tavilyai has just begun! https://t.co/8TheQp5ReJ

Media from the original post
♡ 19 likes↻ 2 reposts↳ 4 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

Final sessions of Interrupt NYC 🎙️ Fireside Chat w/ @RogoAI CEO & Co-Founder @gabestengel 🎙️ Evaluating Agentic AI at Scale with @linkedin https://t.co/kLEMO6bftf

Media from the original post
♡ 13 likes↻ 1 reposts↳ 5 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Before 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

Media from the original post
♡ 11 likes↻ 0 reposts↳ 4 replies
Collected original
LangChainVideo
View original post on X ↗
Coding & agents𝕏

A 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

Media from the original post
♡ 30 likes↻ 2 reposts↳ 6 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Another awesome feature in Managed Deep Agents 0.8

♡ 24 likes↻ 0 reposts↳ 1 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Managed Deep Agents 0.8 makes the Slack experience even better!

♡ 18 likes↻ 0 reposts↳ 2 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Introducing 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

Media from the original post
♡ 72 likes↻ 8 reposts↳ 10 replies
Collected original
VideoExternal link
View original post on X ↗
Coding & agents𝕏

confidence 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

Media from the original post
♡ 24 likes↻ 6 reposts↳ 7 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

Up next at Interrupt 🎙️ Fireside Chat w/ @OpenRouter CEO & Co-Founder @alexatallah 🎙️ Building Engine: How we approach agent improvement w/ @bentannyhill https://t.co/0u7XviPsOJ

Media from the original post
♡ 8 likes↻ 2 reposts↳ 4 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Interrupt NYC Swag spotlight: ⌨️ A clicky fidget keycap ❄️ LangChain Sweatshirt 🖊️ Pens https://t.co/iEZPrgo5gV

Media from the original post
♡ 32 likes↻ 0 reposts↳ 2 replies
Collected original
LangChainVideo
View original post on X ↗
Video & motion𝕏

Learn 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

Media from the original post
♡ 58 likes↻ 5 reposts↳ 6 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

The LangSmith Engine that could (be won) https://t.co/RENVfRAGO5

Media from the original post
♡ 17 likes↻ 0 reposts↳ 0 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Introducing 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
Collected original
External link
View original post on X ↗
Coding & agents𝕏

1️⃣ 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

Media from the original post
♡ 9 likes↻ 1 reposts↳ 1 replies
Collected original
Thread
View original post on X ↗
Coding & agents𝕏

What 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
Collected original
View original post on X ↗
Coding & agents𝕏

After 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

Media from the original post
♡ 21 likes↻ 2 reposts↳ 4 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Introducing 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

Media from the original post
♡ 133 likes↻ 11 reposts↳ 12 replies
Collected original
VideoExternal link
View original post on X ↗
Video & motion𝕏

Read the full rules here 👇 https://t.co/mL4wHtRDsJ

♡ 9 likes↻ 1 reposts↳ 0 replies
Collected original
ThreadExternal link
View original post on X ↗
Coding & agents𝕏

Dependabot 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

Media from the original post
♡ 147 likes↻ 16 reposts↳ 46 replies
Collected original
GitHub CopilotVideo
View original post on X ↗
Coding & agents𝕏

Special guests at the LangChain Demo Station: @nvidia!  Stop by and say hello during lunch! https://t.co/lAhK1gQSXp

Media from the original post
♡ 7 likes↻ 0 reposts↳ 2 replies
Collected original
LangChain
View original post on X ↗
Coding & agents𝕏

And it’s time for a break! Grab lunch before we kick off the next round of sessions + workshops! https://t.co/P5oPCJ14UM

Media from the original post
♡ 12 likes↻ 0 reposts↳ 1 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Introducing 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
Collected original
View original post on X ↗
Coding & agents𝕏

At Interrupt? 🕹️ Try your hand at Agent Claw 🚂 Play for a LangSmith Engine https://t.co/Os10m96ktZ

Media from the original post
♡ 14 likes↻ 2 reposts↳ 3 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

New 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
Collected original
v2
View original post on X ↗
Coding & agents𝕏

Next 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

Media from the original post
♡ 8 likes↻ 0 reposts↳ 2 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Just 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

Media from the original post
♡ 54 likes↻ 9 reposts↳ 8 replies
Collected original
DaVinci Resolvev2VideoExternal link
View original post on X ↗
Coding & agents𝕏

Happening now: @modal Fireside Chat w/ CEO + Co-Founder @bernhardsson https://t.co/ajl2okw6FK

Media from the original post
♡ 15 likes↻ 0 reposts↳ 2 replies
Collected original
View original post on X ↗
Coding & agents𝕏

In 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

Media from the original post
♡ 27 likes↻ 3 reposts↳ 3 replies
Collected original
v2External link
View original post on X ↗
Video & motion𝕏

If 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

Media from the original post
♡ 3 likes↻ 0 reposts↳ 2 replies
Collected original
VideoExternal link
View original post on X ↗
Coding & agents𝕏

Accessibility 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

Media from the original post
♡ 71 likes↻ 3 reposts↳ 2 replies
Collected original
VideoExternal link
View original post on X ↗
Coding & agents𝕏

Packed house for @hwchase17’s opening keynote! https://t.co/vZvof0CEIC

Media from the original post
♡ 29 likes↻ 2 reposts↳ 2 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Join the opening keynote livestream: https://t.co/SNB4bvlcpe https://t.co/LIozexLwJw

Media from the original post
♡ 11 likes↻ 2 reposts↳ 1 replies
Collected original
VideoExternal link
View original post on X ↗
Coding & agents𝕏

✨ 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
Collected original
External link
View original post on X ↗
Coding & agents𝕏

🔴 Going live in 15!!!

♡ 6 likes↻ 0 reposts↳ 0 replies
Collected original
View original post on X ↗
Coding & agents𝕏

It wouldn’t be an agent conference without humans in the loop. https://t.co/QSVkWZa7wt

Media from the original post
♡ 29 likes↻ 3 reposts↳ 6 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

At Interrupt? 

Grab some breakfast + coffee from our sponsors at @focused_dot_io + @FactoryAI before we kick off! https://t.co/LtTldx4DYC

Media from the original post
♡ 8 likes↻ 1 reposts↳ 1 replies
Collected original
View original post on X ↗
Coding & agents𝕏

Want 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
Collected original
View original post on X ↗
Coding & agents𝕏

More #GitHubUniverse sessions just dropped 🆕 Grab your pass, and we'll see you October 28-29 🌁 https://t.co/P78J1QQHjA https://t.co/b8pQGJleWS

Media from the original post
♡ 65 likes↻ 5 reposts↳ 3 replies
Collected original
External link
View original post on X ↗
Video & motion𝕏

💚 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

Media from the original post
♡ 40 likes↻ 0 reposts↳ 2 replies
Collected original
VideoExternal link
View original post on X ↗
Models𝕏

We 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.

Media from the original post
♡ 24 likes↻ 3 reposts↳ 7 replies
Collected original
Thread
View original post on X ↗
Models𝕏

Read our research blog to learn more about Muse Realtime Avatar: https://t.co/pVq9K0fxCG

♡ 21 likes↻ 2 reposts↳ 4 replies
Collected original
ThreadExternal link
View original post on X ↗
Coding & agents𝕏

benched

♡ 8 likes↻ 0 reposts↳ 9 replies
Collected original
Thread
View original post on X ↗