46 original posts · author attribution and direct source links
OpenAI
@OpenAIGPT-6 Astra Pro in ChatGPT got an upgrade with faster responses and improved use of plugins and tools. And now, multiple agents can tackle different parts of a task in parallel. You can follow each agent’s progress and open completed tasks to review their work. Now available to Pro users in the Chat tab.
Cursor
@cursor_aiCloud agents can now build interactive canvases. Ask for a dashboard or report while the agent works, then share the finished canvas with your team as a link. https://t.co/cLGgGLKrBT
Anthropic
@AnthropicAINew from our STEM Fellows Program: Designing more efficient quantum circuits with Claude. Given plain-language instructions, Claude Mythos 5 designed quantum circuits that improve on the best published ones, sometimes by an order of magnitude or more. More efficient circuits reduce the resources needed by quantum algorithms, which could bring quantum computing applications in chemistry and materials science within reach sooner. Read more: https://t.co/QCvoJLDmBo
OpenAI Developers
@OpenAIDevsHere’s how our engineers use Codex at OpenAI to dig through our codebase, find what needs attention, and chip away at the maintenance backlog:
Mistral AI
@MistralAITurns out le Chonk is into rocket science. Mistral Large 4 scoring well in engineering and astronomy on Ulam’s private benchmark, STEMBench: https://t.co/OW3reppzWN https://t.co/3BbnbEuYvP
OpenAI Developers
@OpenAIDevsPut your dot on call. Ali, an engineer at OpenAI, used his dot to triage an on-call incident at 3am. His dot investigated the issue and started a Codex thread, so he could steer the work from his phone in the ChatGPT app. https://t.co/xLhtGUSzsx
OpenAI Developers
@OpenAIDevsBuilding apps with GPT-Live-1? Give them a voice that fits. Here’s how to shape a voice with a prompt or choose from new international preset voices: https://t.co/HtMsozvqE7
Google DeepMind
@GoogleDeepMindFour Gemini 4 Argon agents beat Minecraft from scratch in 27 hours. Operating in a sandbox using only code and text, they wrote 2,783 programs, divided up jobs over chat, shared notes, and debugged errors together - all with no human help ↓ https://t.co/uyIhDOQXGT
Lummox
@Lummox_ethhttps://t.co/P9t6FtO8Ms
swyx
@swyxit finally happened, i'm in a zoom with 3 ai's golden age of solipsism https://t.co/so3MBKRPyd
Cognition
@cognitionWe’ve partnered with @ndstudio to launch American Forge. It’s a six-month residency for exceptional engineers to embed inside the government and build software that affects hundreds of millions of people. Right now, a small team can do more than ever - including in public service! Applications are now open.
Google DeepMind
@GoogleDeepMindTogether with scientists around the world, our models and tools are helping make disease more detectable, treatable, and preventable. 🧬 From pinpointing rare genetic variants to speeding up drug discovery, here’s how we’re helping turn lab breakthroughs into real-world care → https://t.co/sM5G0CLcKJ
Visual Studio Code
@code🤖 Stop Guessing Which AI Model to Use! In this video we walkthrough model exploration and comparison. #vscode #visualstudiocode #foundrytoolkit https://t.co/oIvSAbi69F
GitHub
@githubhttps://t.co/otZg9dIh7u has fully moved off CSS-in-JS to CSS Modules, resulting in 55% less server-side render time and 25% faster component init. https://t.co/0AV4Fr3RSo
swyx
@swyxi've been waiting to launch this show for almost a year! thanks to the Testers and to @NehallAgrawal @KaylinWardley for helping me put this together! some behind the scenes from the shoot of our latest show!! https://t.co/YADPOxPqCY
Visual Studio Code
@code🚀 Explore interactive canvases for agent workflows, seamless chat handoffs, and new Markdown editing features. 🔗 Check the weekly updates: https://t.co/n3iELLWj1u https://t.co/3usCjIZodt
swyx
@swyxproud to have welcomed @affaan and @absurdistphil to @aidotengineer NYC to launch the new Compute Trading industry and give both engineers and traders the definitive intro to what, why and why now https://t.co/7bBPgrEwmx
Cursor
@cursor_aiThe Environments API is now available in beta. Create and manage cloud agent environments programmatically, including the repos they clone and the environment.json setup they run.
GSAP
@greensock💚 Site of the Day - Vectr Utsubo — @utsuboco & Michele Angeloro ⚙️ ScrollTrigger 🛠️ @threejs, WebGL, Astro, WebGPU, OffscreenCanvas site → https://t.co/vEMIQtLPtc showcase → https://t.co/zGjV9MynPN https://t.co/oCXpiP5ZwO
Framer
@framerCheck out these 4 super interactive components you can build for your website with the Framer Agent. Prompts below ↓ https://t.co/U473NMlvZc
Hugging Face
@huggingfaceLIVE STREAM: New Open Weight Model https://t.co/iBGsMXYfvr
OpenAI Developers
@OpenAIDevshttps://t.co/M0xXGlyiMM
Framer
@framerWe’ve refreshed the Framer Gallery help you explore some of the best websites on the internet and find inspiration for your next project. Explore an expanded range of categories and filter by vibe to find the look and feel you’re after. https://t.co/q5gsKW2uSZ https://t.co/Z4JAPasiV3
Cursor
@cursor_aiCloud agent environments now support up to 500 repos, and large multi-repo environments start 5x faster. See everything new: https://t.co/FfATEvnQdv
LangChain
@LangChainAgents with sandboxes run packages you didn't write. If one is malicious, any credential in the sandbox is exposed. With Managed Deep Agents, the proxy adds your token outside the sandbox, only on calls to services you've allowed. The agent never sees it.
Blackmagic Design
@Blackmagic_NewsColor Fundamentals for Editors Seminar! Join us on Friday 23rd October at 14:00 BST to learn how to balance and match media from different cameras, then begin the grading process to create unique looks, working in both layers and nodes. Learn more at https://t.co/QuUoBrZ7K6 https://t.co/xvKsw7e6K3
Hugging Face
@huggingfaceLIVE STREAM in minutes! Hear from the Reflection team about how they built Beam. Stream: https://t.co/q6OKvCiB9o
LangChain
@LangChain🧵 Behind the scenes of AI Search in LangSmith: TL;DR 1️⃣ SmithDB turns traces into readable trajectories. Structured filters narrow the candidates when you search 2️⃣ A model checks each remaining trajectory against your description and streams back matches https://t.co/YWBjhFkeQ6
OpenAI Developers
@OpenAIDevsThe nine new presets were created with native-speaking actors in French, German, Hindi, Japanese, and Korean. Check out our guide to get started: https://t.co/xetCNTG8Q1
GitHub
@githubWhat are your conference essentials? Grab a #GitHubUniverse pass to join us in-person October 28-29 or sign up to join us virtually ⬇️ https://t.co/rBP7w7Mwjo https://t.co/wzF57AOtt2
Framer
@framer💅🏼
LangChain
@LangChainWhat does it take to move healthcare and life sciences agents from experimentation into trusted production systems? Explore the architectures, evaluation practices, and production patterns teams are using as agents take on more complex work: ➡️ https://t.co/RkfVB7H3zd https://t.co/mQnhuYdZ68
LangChain
@LangChainAt our recent Learning Loop event, @oneill_c from @baseten explained why continual learning keeps breaking, and what to try. Watch the full session ⤵️ https://t.co/USzxElBs5T
Motionographer®
@motionographerHypersail | FutureDeluxe Ferrari’s racing DNA takes to the water. FutureDeluxe’s livery launch film for Hypersail brings the vessel’s materials, solar energy systems and foil technology into focus before it was built. A Ferrari WEC car establishes its immense scale, while rapid cuts and expansive views create a rhythm of precision and speed. Designed, directed and produced by FutureDeluxe, with audio by group-project and colour by Alex Gregory at Harbor. Watch the full film: https://t.co/ZhPPyX4NzE #Hypersail #Ferrari #FutureDeluxe #MotionDesign #CGI #mtngrphr #motionographer
LlamaIndex 🦙
@llama_indexDoc of the Week: VL-DocIR’s, a new paper on long-document retrieval. Table 2, where the “Data Source” header spans Wiki, arXiv, PubMed and SEC and stops one column short of Total. LlamaParse Agentic Plus kept that span, along with all 35 counts and every label. Try it on your own research paper ->
swyx
@swyx@cjav_dev @aiDotEngineer @ricmac @latentspacepod and Anthropic's Flows/multiagent workshop is live! thanks so much to @katelyn_lesse for helping set this up, and thanks to CJ and Harrison for an incredible workshop! https://t.co/7Fyakm45B9
GitHub
@githubNew in GitHub Transparency data: Learn about government takedown requests and reporting, and get a recap of 2026 state legislative sessions affecting open source. https://t.co/kLiA6Vw7XM https://t.co/VBICBl0l4G
swyx
@swyx@affaan @absurdistphil @aiDotEngineer full talk written up: https://t.co/EpmPzFAsgJ
Adobe Video
@AdobeVideoThe real win is getting to be your video editing software. But the technical win is “Engineering, Science & Technology Emmy Award for Outstanding Achievement - Adobe Premiere,” accepted by Laura Teodosio (Senior Director of Product, Digital Video and Audio) and the Adobe Video team. We are beyond honored to be recognized by the very community we’ve made it our mission to support, uplift, and export. https://t.co/1iX0e8u9Nn
School of Motion
@SchoolOfMotion💪 5 storyboard checks that catch problems before you animate! In this week's blog, we look at how to catch confusing action, awkward cuts, and rushed timing BEFORE you animate, with five practical storyboard checks you can run using paper, a pen, and a script! Read the full blog post ➡️ https://t.co/VyC2cf1ytB
LangChain
@LangChainWhen you search, structured filters like a time range narrow the candidates first. Then a small, fast model checks each remaining trajectory against your description, with many checks running in parallel. Each one usually takes under half second. Matches stream back as they’re found, so you don’t wait for the full scan.
LlamaIndex 🦙
@llama_indexSource: Table from Simon Ott et al., VL-DocIR, CC BY 4.0 (https://t.co/TUmK5MKeEg).
Adobe Video
@AdobeVideoYou are what you create. 🎨: IG | masd.lab https://t.co/2hTKZPaL3x
LangChain
@LangChainAI Search reads each trajectory within a fixed token budget. Most questions about behavior only need a small slice, and we checked that on 150 conversations from Open SWE, the coding agent our team uses every day. ✅ The median ran 84K tokens ✅ About 1.5K of that was the user’s messages and the agent’s final reply ✅ Roughly 3/4 was tool output: file reads, shell commands, test logs https://t.co/rC1M6lvaIH
Framer
@framerBento Section: Create a four-card bento portfolio: rows split 2:1 then 1:2, with 16px gaps. Each rounded card contains a 200px-tall image, title and short caption. Hover shows a pointer only. Clicking morphs the card, image and text into a centered viewer over 0.64s ease-in-out; keep text size stable. Dim and blur the background, lock page scroll, and reveal extra description with a delayed blur-to-sharp fade. Clicking the image, arrow keys or swipes cycles projects with looping 0.4s horizontal slides. Escape or clicking outside reverses the morph into the currently displayed project’s grid card.
Framer
@framerGet the components 👇 https://t.co/VF0WVimzDl
