AI Coding & Agents

Visual Studio Code

@code

🔎 Explore everything that’s new in the full release notes: https://t.co/15Hrd1YVqk Happy coding! 💙 https://t.co/YJQXbZY7EU

Sep 23, 2026, 06:58 PM UTC

♡ 4 likes↻ 0 reposts↳ 0 replies

Visual Studio Code

@code

🚀 The latest @code release makes large agent session lists faster and easier to manage and lets you run agent sessions in Dev Containers, both locally and on remote hosts. 🧵 Here’s what’s new: https://t.co/YJQXbZY7EU

Sep 23, 2026, 06:58 PM UTC

♡ 331 likes↻ 36 reposts↳ 12 replies

Cognition

@cognition

And Devin now works natively with Microsoft 365: grant access to Outlook, Calendar, OneDrive, SharePoint, and Directory, to give Devin all the context it needs to keep working. Permissions are scoped per user and per app, giving your team precise control and flexibility.

Sep 23, 2026, 06:14 PM UTC

♡ 18 likes↻ 0 reposts↳ 4 replies

Cognition

@cognition

Read more: https://t.co/sxYQwfxr0e

Sep 23, 2026, 06:14 PM UTC

♡ 14 likes↻ 0 reposts↳ 2 replies

Cognition

@cognition

In Microsoft Teams, you can now direct message Devin, start a group chat, or spin up Automations from Teams channels, all without leaving the chat. Devin can also @-mention coworkers for questions, send file attachments, or mute itself when its done. https://t.co/8rkjz9VesZ

Sep 23, 2026, 06:14 PM UTC

♡ 33 likes↻ 0 reposts↳ 2 replies

Cognition

@cognition

Devin loves building apps on its own PC. Now, it works even better on yours. Introducing two updates to Devin for Microsoft users: native support for Teams, and a first-party Microsoft 365 integration to connect to your mail, calendar files, chats, and more. https://t.co/lC1Dii9FNK

Sep 23, 2026, 06:14 PM UTC

♡ 315 likes↻ 20 reposts↳ 32 replies

OpenAI Developers

@OpenAIDevs

Bring your next project to life with Codex: https://t.co/Yhq6asiUnX

Sep 23, 2026, 05:58 PM UTC

♡ 61 likes↻ 3 reposts↳ 0 replies

OpenAI Developers

@OpenAIDevs

GPT-Live-1 handles the conversation while the Raspberry Pi sends research and tool tasks to GPT-5.6 Luna via the Responses API. The Pi’s local renderer turns scenes into 128 × 64 pixels. Sid can keep talking while research and rendering happen in the background. https://t.co/mCJbi5AfxA

Sep 23, 2026, 05:58 PM UTC

♡ 88 likes↻ 5 reposts↳ 12 replies

OpenAI Developers

@OpenAIDevs

From figuring out the wiring to debugging “show that on the wall,” @sidrampally shares how he used Codex to turn an LED display into a voice-controlled assistant. Powered by GPT-Live-1 and a Raspberry Pi, it shows weather, subway arrivals, and more: https://t.co/d6wv1qNHzc

Sep 23, 2026, 05:58 PM UTC

♡ 674 likes↻ 40 reposts↳ 54 replies

GitHub

@github

➡️ Coming soon: Let's Learn GitHub Copilot SDK Starting September 24, we'll host beginner-friendly livestreams on how to build agentic applications with the GitHub Copilot SDK, without implementing the agent loop yourself. Includes sessions specifically for .NET and Java development. Sign up for English, Chinese, Portuguese, Spanish, Japanese, or Korean. https://t.co/dl62TnerXt

Sep 23, 2026, 04:15 PM UTC

♡ 260 likes↻ 36 reposts↳ 27 replies

Cursor

@cursor_ai

We've reduced token costs in Cursor by 7% with no drop in agent quality. Savings came from tighter prompts, selective tool loading, better caching, and compressed file reads. https://t.co/EMNxELnfwO

Sep 23, 2026, 03:46 PM UTC

♡ 4.6K likes↻ 196 reposts↳ 250 replies

Cursor

@cursor_ai

Here's how we improved our agent harness: https://t.co/VzcB2yMqxU

Sep 23, 2026, 03:46 PM UTC

♡ 233 likes↻ 16 reposts↳ 17 replies

Visual Studio Code

@code

Visualize Data Structures in VS Code 🤯 If you work with data structures, check out the Debug Visualizer extension for VS Code. It lets you visualize your data while debugging so you can actually watch algorithms and data structures change as your code runs. In this example, see a linked list grow node by node and watch QuickSort move values into sorted order. A great tool for learning data structures, understanding algorithms, and debugging complex code. #VSCode #Programming #Coding #DataStructures #Developer

Sep 23, 2026, 02:02 PM UTC

♡ 838 likes↻ 105 reposts↳ 18 replies

swyx

@swyx

@latentspacepod https://t.co/oloSDxf0q7

Sep 23, 2026, 06:43 AM UTC

♡ 18 likes↻ 2 reposts↳ 10 replies

swyx

@swyx

can confirm. ran @latentspacepod AINews side by side with 6 Sol and the difference was night and day: https://t.co/oloSDxf0q7 5.5 Opus is the new default model for AINews going forward. so much more concise and tasteful reporting, with much less slopese than even 5 Opus. https://t.co/P6AXDlBKNP

Sep 23, 2026, 06:43 AM UTC

♡ 219 likes↻ 14 reposts↳ 158 replies

GitHub

@github

Should you review your AI-generated code? Is RAG over? Did Skills make MCP obsolete? The GitHub Podcast responds to these hot takes 👇 https://t.co/7cOBj3MtKW

Sep 23, 2026, 02:30 AM UTC

♡ 96 likes↻ 12 reposts↳ 29 replies

OpenAI Developers

@OpenAIDevs

Thanks to @cerebral_valley for co-hosting our GPT-6 hackathons in SF and NYC 🤝

Sep 22, 2026, 10:19 PM UTC

♡ 33 likes↻ 0 reposts↳ 1 replies

OpenAI Developers

@OpenAIDevs

Get lost in your side projects. One builder at our GPT-6 hackathons brought real star maps and Astra to help you find your way home. https://t.co/D9lkBA7ar4

Sep 22, 2026, 10:19 PM UTC

♡ 615 likes↻ 28 reposts↳ 33 replies

OpenAI Developers

@OpenAIDevs

Tune caching for your application: – Choose which prompt prefixes to reuse with explicit cache breakpoints. – Adjust reasoning effort and tool availability while preserving cached context. – Prewarm shared context so responses start sooner. https://t.co/ILhdJ9uWcZ

Sep 22, 2026, 09:13 PM UTC

♡ 156 likes↻ 8 reposts↳ 6 replies

OpenAI Developers

@OpenAIDevs

We’ve improved prompt caching in the API for GPT-6, helping agents run faster and cost less. Higher cache-hit rates by default mean more input tokens benefit from cached-input discounts of up to 90%. https://t.co/NZse8QKr8G

Sep 22, 2026, 09:13 PM UTC

♡ 1.7K likes↻ 67 reposts↳ 89 replies