47 original posts · author attribution and direct source links
ClaudeDevs
@ClaudeDevsClaude Managed Agents dynamic workflows are now available in public beta. It's a new type of multiagent orchestration, built for your most ambitious workloads. A lead agent writes a plan that runs across many agents in phases, combining the results at the end. https://t.co/hEExShsVku
Stanley Wei
@StanleyWei4748AI is already smart enough. Real-world tasks are still slow, expensive and unreliable, because we hand AI a computer built for humans, then wrap it in a heavy harness. AI doesn’t need to get smarter. It needs a computer built for it. Today we’re releasing Pine Computer https://t.co/8NMf7Wc0gt
OpenAI Developers
@OpenAIDevsNow in beta: composer predictions in Codex for Pro users. Codex can now suggest your next message based on your conversation and how you talk to it. One of the most loved new features we've ever tested internally. https://t.co/0u8d2a3feS
Qwen
@Alibaba_Qwen🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available! Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture. Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene. Start directly with Diffusers: load QwenImage21Pipeline and the checkpoint’s recommended 8-step sampling schedule is ready to go. 🌐 Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow. 🤖 ModelScope: https://t.co/Cixiro51v8 🤗 Hugging Face: https://t.co/4GqXcYeAmB 🔗 Pro API: https://t.co/fw2am7VCP7 🔗 Turbo API: https://t.co/qmDvTqiVZK What will you create with 8 steps? Share your results with us!
OpenAI Developers
@OpenAIDevsThe attention to detail is a little concerning.
Anthropic
@AnthropicAIWe’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports. Today’s report describes four types of behaviors we’ve identified during evaluations and internal use. In each, Claude acted on real websites or systems in ways we didn’t intend, sometimes by working around a restriction instead of stopping. All cases had minimal real-world impact. From an alignment and security perspective, we consider these behaviors significantly less severe than the cybersecurity incidents we reported in July and September. Read the full report: https://t.co/mGeVIBgdou
Cognition
@cognitionYou can use any personal ChatGPT plan with Devin Just connect your Go, Plus, or Pro plan to Devin and all GPT model usage will draw down from you plan's quota https://t.co/7vVFQq3IAB
OpenAI Developers
@OpenAIDevsAn update for builders using Codex on Windows: We’ve built a new sandbox mode using @Microsoft’s Execution Containers (MXC) for faster setup, stronger network enforcement, and granular file access controls. Requires a compatible Windows 11 device.
swyx
@swyxgoing rate for this role is between 5-50m comp package btw at the frontier agent labs
beamnxw ./
@beamnxwOpus 5.5 can run a whole motion design studio Sell a 20-second launch clip built from real product screens Copy the motion engineering prompts and delivery process Build your offer before the next product launch ↓ https://t.co/KjiDrYRDjQ
Qwen
@Alibaba_QwenA week of free access to Qwen3.8-Max, Qwen3.8-Flash, and Wan3.0 on @gmi_cloudis live. Explore what you can build with us now. 🙌
Simon Willison
@simonwI built a new feature for my blog entirely by voice with Codex Desktop, while I was cooking dinner https://t.co/dQwOlgFeKT
Simon Willison
@simonwWhat's the best open weight Mixture-of-Experts LLM for coding that fits in less than 60GB of RAM? I think MoE might be necessary to get reasonably interactive speeds on the hardware I have access to - I want something faster than 12 tokens/second
OpenAI Developers
@OpenAIDevsAvailable in beta for Pro users in the Codex desktop app, for local tasks. Hit “Tab” to accept a suggestion, edit it if needed, then send. You can turn composer predictions off in Settings. https://t.co/Go9GsTLCI3
Google AI
@GoogleAIIt’s Friday 🎉 Here’s a look at this week’s announcements: — https://t.co/aIbQoguyFu is now available globally in English, allowing anyone to use our detector portal to easily verify if images, video, or audio files were AI-generated by Google or industry partners — Nano Banana 2.1, featuring leaps in visual design, subject consistency, and precise spot editing that lets you change specific details without altering the whole image — EmbeddingGemma 2, our first natively multimodal open model that unifies text, images, video, audio, and code into a single space for on-device embeddings — @GoogleGemma 4 paired with BOTANIC-1, a specialized AI trained on plant DNA, to rapidly pinpoint the exact mutations that make crops thrive — Gemini agent for your business, a universal cloud agent running 24/7 to get your work done — Guided Vision in Gemini Live, offering real-time visual assistance and dynamic audio descriptions via your camera, built alongside the blind and low-vision community
Visual Studio Code
@code📝 Your Entire Agentic AI Workflow Now Inside VS Code In this video, we run through installation, logging to Microsoft Foundry and an overview of the UI. https://t.co/OHcn9P7RV5
Qwen
@Alibaba_QwenPics: https://t.co/thKNW8wr4W
Vercel
@vercelEngineers at @RilletHQ run @eve agents on Vercel that turn customer requests into PRs. New features reach production in 2 hours, and merged PRs have tripled. https://t.co/eM0scpkAsL
swyx
@swyxrecap of last time this discourse happened for those who are insufficiently online https://t.co/mI2kqulWLi
LangChain
@LangChainThe 3 questions every agent builder should be able to answer: ✅ Where the agent fails ✅ How to reproduce it ✅ How to make it stop Watch @JakeBroekhuizen’s session: https://t.co/yQkzaV0GVt https://t.co/YFfv9Dtf52
Simon Willison
@simonwI like Qwen3.5-35B-A3B for this, wondering what else is out there that might be a bit more recent and pack a little more of a punch
GitHub
@githubGitHub Universe is typing... Cooking up something fun for you to build ⌨️ Make sure you grab your in-person pass ⬇️ https://t.co/dEAi3Xv1Nt https://t.co/gBWlEjyDUM
LangChain
@LangChain✅ 60k queries handled ✅ 500+ customer accounts ✅ 85%+ of sessions resolved without a support ticket ✅ 250+ cases auto-detected + escalated to the right team @SnykSec Assist. Built on LangChain + LangGraph. Observability in LangSmith. Full story: https://t.co/oblUQ4totV https://t.co/OZU048uVqd
GSAP
@greensock💚 Site of the Day - CRL, Creative Reference Library Bimo Tri — @bamojk Josh Bendall — @_joshbendall ⚙️ SplitText, Text, CustomEase 🛠️ @threejs, @webflow, WebGL site → https://t.co/vw27PnAAFs showcase → https://t.co/zGjV9MynPN https://t.co/2sRxzKa1mb
Qwen
@Alibaba_QwenEdit: https://t.co/xQ9ftFg4Hy
LlamaIndex 🦙
@llama_indexWhat happens when a table contains tables? Usually, a mess. With LlamaParse, it comes out clean. Doc of the Week: Micron’s latest earnings deck. Even with two business units and same row names, LlamaParse keeps all 18 values under the right header. Try it out on your own earnings deck: https://t.co/p5fnaPmAP6
Cognition
@cognitionLearn more: https://t.co/78m3g1IyK8
LangChain
@LangChainNew in Managed Deep Agents 0.9: Reactions API for @SlackHQ Channels. When it comes to building effective user agent experiences, loading states are underrated. Now, you can build loading states and receipts using either heuristics, decision models, or custom logic. https://t.co/94x0p5zDlZ
LangChain
@LangChainWe simplified agent authentication, memory, and channels, and brought in web search as a pre-built tool for Managed Deep Agents. Watch @VictorMoreira16’s full Interrupt NYC session for an inside look: https://t.co/W2CQTpwhdv https://t.co/fn4D8JzH6A
Framer
@framerDrag interactions, cursor states, and subtle fades at the edges. See how @masonwenlaunch used the Framer Agent to build the 3D carousel for @RED’s 20th anniversary site. https://t.co/TbVu9ALONI
LangChain
@LangChainLangSmith Signals from the last month: ✅ Claude Sonnet 5: #9 to #2 in model adoption. 51% more orgs using it ✅ gpt 5.6 luna: #3 to #1 in call footprints. 65% more calls ✅ Two open-weights models are now in the adoption top 10, but not for call volume ✅ Smaller, faster models dominate call footprints
GitHub
@githubEver been to a hackathon? Follow participants throughout their day, from badge to the final demo. What you can learn from attending a hackathon ⬇️ https://t.co/e2o6EmOBU4 https://t.co/0PQvBBgVmK
OpenAI Developers
@OpenAIDevshttps://t.co/sItn14uFFH
Simon Willison
@simonwExample prompt: https://t.co/qSsBnLwly5
Blackmagic Design
@Blackmagic_NewsIntroduction to Blackmagic Cloud Seminar! Join us on Wednesday 14 October at 15:00 SGT to learn how to get started with Blackmagic Cloud. You'll discover what Cloud Storage, Project Server and Presentations each do, how profiles differ and how to rent and assign DaVinci Resolve licenses. Learn more at https://t.co/M4cFe5uISo
LangChain
@LangChainExperience the best of Interrupt. Access our archive and watch every session on-demand: https://t.co/hL8WUWHJ9e
swyx
@swyxif you cant hire for it, my team will do oneoff consult for you, get in touch business@latent.space https://t.co/TrsDS8PK4l
School of Motion
@SchoolOfMotion🛠️ 5 Rive Animation stress tests and how to fix what breaks! This week we walk you through 5 different stress tests for your Rive animation, and how to fix things if they break 💪 Full blog post ➡️ https://t.co/6QwR9YGLNR Ready to dive into Rive? Check out our Rive Academy, including the brand new course - Rive Academy: Data Binding! ➡️ https://t.co/uA7jrFaGY7
Simon Willison
@simonwAdmittedly I guess this is a pretty incredible troll targeted at people who say "it shouldn't be called artificial intelligent because it's not actually intelligent" Do they now feel obliged to defend the old name against the new one?
LangChain
@LangChain.@Factory_AI is sponsoring Interrupt London! Stop by their booth during the event and go hands-on with the autonomy stack for enterprise teams. https://t.co/eFW77eyVGW
swyx
@swyxmost of you are unfortunately not qualified but there is somewhat a path https://t.co/l29L1HJVej wrote down mine in @Coding_Career 6 years ago and you can now get it free or on amazon https://t.co/P0wqju1nsk didnt intend to relaunch CC today but eh why not
Qwen
@Alibaba_QwenThanks for the support! @gmi_cloud
GitHub
@github#GitHubUniverse is just around the corner. 👀 What will you be adding to your agenda? From verifying AI-written code to securing npm dependencies, here are the sessions to keep in mind at this year's event. ⬇️ https://t.co/20XSRpDNxG
swyx
@swyxto paraphrase modern family, there are 5 things wrong in this tweet. the talented {role} will already have posts covering most of them https://t.co/TEtI8UL5TA
Adobe Video
@AdobeVideoBibin's Premiere edit packs a punch. 🥊 🎨: IG | bibineyy_ https://t.co/KTyfNGUKT3
LangChain
@LangChain@factory_ai Learn more about Interrupt, The Agent Conference by LangChain and RSVP: https://t.co/GCNitijjvm
LlamaIndex 🦙
@llama_indexSource linked here: https://t.co/Q3FtQcyuaW
