36 original posts · author attribution and direct source links
Deep Barot
@deepcabinwalaEveryone got a coding agent. Nobody got a QA engineer. Until today. Meet Ship, your Autonomous Quality Engineer. It tests deployed PRs, reproduces bugs from Slack and Linear, and hands Claude or Codex the context to fix them. Try it free: https://t.co/iKhsWrVxu9 https://t.co/lgTklYYuwT
codila
@0xCodilaIt's probably the easiest way to make money with ONLY AI in 2026... Companies are already offering ~$500 for 15-sec videos made with Opus 5.5 & Fable 5.5 In this article, I'll walk you through building a motion studio and share offers from scratch: https://t.co/cPyuxX3x5E
Cognition
@cognitionIntroducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work At night Devin self-improves its memory to remove stale records and discover latent information We are creating an OSS standard called Agent Memory Repo: https://t.co/b6qzEJsaeT https://t.co/G3o1WQqQbN
OpenAI
@OpenAIWe're expanding our approach to content provenance to include text in response to EU regulatory requirements, while recognizing the significant limitations of current text watermarking technology. Our tools already help verify whether an image or audio file was created with our models. This work builds on those efforts to help people better understand when content may have been generated or edited with an OpenAI model. In the EU, we’ll start watermarking eligible text from ChatGPT and Codex over the coming weeks to comply with the EU AI Act. Customers using our API can turn on text watermarking for select models worldwide today.
Rahul
@sairahul1AI influencers are taking over TikTok and Instagram. You can now create one in 10 minutes, put it into videos already going viral, and actually monetize the views. I broke down the full system + every prompt you need to build one: https://t.co/ERRaRO8hvS
rari
@0xwhrrariGrok Bot can learn from your whole team One bad memory can mislead everyone What to save, what to keep private, and when to check the source A practical guide to Grok Bot memory engineering Bookmark and read below ↓ https://t.co/3SD7Ey9Q9N
LlamaIndex 🦙
@llama_indexOCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text it got. Tables get flattened, charts disappear, and multi-column layouts come out scrambled. Nothing checks the output. Agentic OCR treats parsing as a loop instead: ✅ layout-aware reading order ✅ smart routing of hard elements to the right model ✅ multi-pass verification and self-correction ✅ multimodal parsing of charts, images, and complex tables Logan Markewich, LlamaIndex's Head of Open Source, wrote about what that shift looks like in practice and where it's still struggling. Link to the breakdown in the comments below.
Cursor
@cursor_aiYou can now steer Cursor SDK agents while they run. run.steer() adds your message to the next turn. If a subagent is mid-task, it moves to the background and keeps working. https://t.co/1GHeV6kfKC
OpenAI Developers
@OpenAIDevsIf you live in the terminal, this one’s for you. Watch how to start tasks by voice, manage agents across projects, and explore another direction in a separate worktree with the Codex CLI. https://t.co/Q4GmBprj27
Simon Willison
@simonwI re-ran an experiment @colin_fraser ran against GPT-4o a while back to see how good it was at adding long numbers, only this time I tried Qwen 3.8 27B running locally in both reasoning and non-reasoning modes https://t.co/IOufJIA4N9 https://t.co/4kB33NCPcO
Google AI
@GoogleAIhttps://t.co/cdfqoSOtJm
Rossst.03
@Rossst_03Most on-chain bots lose by being fast but wrong. The winners do three things before the block closes: detect, simulate, include. In this article I show EXACTLY how to build an on-chain HFT bot that trades every block, from scratch. https://t.co/HYApyAT9ha
OpenAI
@OpenAIWhen possible, we want to give people a choice—and be clear about what watermarking can and can’t do. A text watermark helps answer one question: “Was this likely generated by an OpenAI model?” It works by embedding an invisible statistical signal in text as it’s generated. A detector can look for this signal, and it doesn’t add visible marks or special characters. It doesn’t say who originally wrote the text or who owns it. It doesn’t identify a person, organization, account, conversation, or prompt. In our testing, watermarking hasn’t affected how capable or fast our models are, or how their responses read.
GSAP
@greensock💚 Site of the Day - Agrumea Farm Studio K95 & Danilo De Marco ⚙️ ScrollTrigger 🛠️ Three.js, Web GL site → https://t.co/6uSGb1greV showcase → https://t.co/zGjV9MxQ0f https://t.co/JEoFHfYa8K
OpenAI
@OpenAIWatermarks have limits. They’re often undetectable, especially in short passages. Rewriting or translating text can completely remove the watermark. That’s why, for now, only approved researchers will have access to our detector, so they can help us evaluate and improve the technology. We’re treating text watermarking as an ongoing area of research. We’ll keep testing and improving, with feedback from users, developers, policymakers, and researchers. https://t.co/2QUil8oWdB
Framer
@framerImprove your site’s SEO with the Framer Agent. Use the /seo-check skill in the Agent chat to review and improve page metadata, social previews, image alt text, and other essential SEO settings. https://t.co/pLAlKwUHcQ
Cognition
@cognitionIn early experimentation we saw a swarm of Devins using the memory as a way to coordinate at large scale without us prompting them to (we promise they didn’t hack anyone)
Cognition
@cognitionRead more about memory and dreaming at: https://t.co/yh5nLxFCAy
Visual Studio Code
@codeWhat do Atom, VS Code, and Zed have in common? 👀 A story of ambitious ideas, performance, and the decisions that helped shape the future of code editors. 🎬 The Story of VS Code: https://t.co/Q7cZIVj0d0 #vscode #storyofvscode https://t.co/SLqlnG3Dac
Cursor
@cursor_aiBackground subagents now report back. Their results return to the parent as a follow-up turn on the same run, so stream() and wait() carry through until every subagent finishes. https://t.co/917fsWsG4k
Blackmagic Design
@Blackmagic_NewsBlackmagic Cloud Store 2.1.1! Adds support for Mac OS Golden Gate to all Blackmagic Cloud Store models. Download now from https://t.co/L43bw4dW6w https://t.co/54jOI9Ll6H
LlamaIndex 🦙
@llama_indexRead our take here: https://t.co/xJsRJx7VGL
School of Motion
@SchoolOfMotionThis week non-destructive AI relighting comes to Photoshop, Blender is officially heading to Android tablets, and Cinema 4D now connects directly to Claude via MCP. It's Motion Mondays! Watch the full episode now ➡️ https://t.co/J2g9vT6VrY https://t.co/Zg5YSFgExV
OpenAI Developers
@OpenAIDevsAll in pursuit of a better burrito 🌯
LangChain
@LangChainAdding a new feature to @theziphq's agent used to take weeks. Their team would have to hand-build the code for LLM calls, storage & context. They rebuilt their chatbot on LangGraph + LangSmith, and every trace was there without them writing a single line of code. Full story ⤵️ https://t.co/2dvmGkdk2T
Motionographer®
@motionographerWatch your 6! | Cub Studio Felix the Cat has a watch to steal. Cub Studio brings his familiar mischief into a 3D world for Bremont, pairing a playful heist with the watchmaker’s aviation history. Directed by Fraser Davidson, with watch rendering by Henry Patterson and animation by Davidson, Sean Proctor, and Alex McDowell. Watch the full film: https://t.co/LTsh6QyZE8 #MotionDesign #Animation #CharacterAnimation #3DAnimation #CubStudio #FelixTheCat #Bremont #mtngrphr #motionographer
Cursor
@cursor_aiCustom tools can now carry MCP annotations like readOnlyHint and destructiveHint, so the model can tell a lookup from a delete before it calls one. https://t.co/EYrm33ggGZ
Cursor
@cursor_aiYou can also replace Cursor's system prompt with your own. Rules, skills, and tool schemas still load. We're enabling it account by account. https://t.co/OuGffP1Mre
LangChain
@LangChainIn our Deep Life Sci Workshop, we’ll work through a real research-agent workflow and explore how teams can: ✅ Connect agents to scientific data and research sources ✅ Trace agent reasoning and tool usage ✅ Evaluate agent performance ✅ Identify and fix issues using traces ✅ Improve complex research workflows over time 🌎 NAMER: https://t.co/VmxkURiL2n 🌍 EMEA: https://t.co/4vyb0ZdZyT
Cursor
@cursor_aiSteering and system prompts work with local TypeScript agents. Background subagent results come back locally in TypeScript and Python. See everything new in the SDK: https://t.co/rHyp0i3vUu
LangChain
@LangChainAttending @WorldSummitAI? ⛴️ Don’t miss our evening tasting tour of Amsterdam by boat and by foot featuring @Elastic and @GoogleCloud on October 7th 🚶 Space is limited, RSVP today! https://t.co/9vURLJf17n
LangChain
@LangChainAt Interrupt NYC, @hwchase17 kicked off our agent conference with a session on owning your intelligence, why so many teams care about it right now, and our latest launches. ⏯️ Watch the full session: https://t.co/TTMy5OQVWy https://t.co/mbb0teAhnr
LangChain
@LangChain.@p0 is sponsoring Interrupt London! Stop by their booth for a live demo of the infrastructure that lets AI search, extract, monitor, and reason over the web. https://t.co/B3eDNToo41
LangChain
@LangChain🗽 Every session from Interrupt NYC, now on demand. ⏯️ Access the archive https://t.co/hL8WUWHbjG
Framer
@framerCopy the Skill ↓ https://t.co/X8CJkBiqQr
LangChain
@LangChain@p0 Learn more about Interrupt, The Agent Conference by LangChain and RSVP: https://t.co/GCNitijjvm
