AI Coding & Agents

OpenAI Developers

@OpenAIDevs

GPT-6 Sol and GPT-6 Luna are available in the API and rolling out in Codex and ChatGPT Work for Plus, Pro, Business, and Enterprise users. https://t.co/fv2OS3jEI3

Sep 22, 2026, 06:14 PM UTC

♡ 180 likes↻ 8 reposts↳ 5 replies

OpenAI Developers

@OpenAIDevs

GPT-6 Sol and GPT-6 Luna build on Astra’s alignment advances, showing improvements over the GPT-5.6 Sol and GPT-5.6 Luna models in our alignment evaluations. https://t.co/zdJfhce2O0

Sep 22, 2026, 06:14 PM UTC

♡ 174 likes↻ 4 reposts↳ 4 replies

Cognition

@cognition

On FrontierCode 1.1, our benchmark for real-world engineering tasks that grades mergeability and quality, Opus 5.5 scores 65.3% on Extended — taking the leading spot from Fable 5 at a fraction of the cost. Read more: https://t.co/ELoIAbeica

Sep 22, 2026, 05:35 PM UTC

♡ 21 likes↻ 1 reposts↳ 1 replies

Cognition

@cognition

Try it in Devin Desktop and Devin CLI: https://t.co/y3humFMnN0

Sep 22, 2026, 05:35 PM UTC

♡ 11 likes↻ 0 reposts↳ 1 replies

GitHub

@github

🚀 @AnthropicAI's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and @code. https://t.co/tt9Pf4wAmv

Sep 22, 2026, 05:34 PM UTC

♡ 375 likes↻ 44 reposts↳ 40 replies

LlamaIndex 🦙

@llama_index

The fastest PDF-to-Markdown parser just got faster. ⚡️ With LiteParse v2.14.6, text-based PDFs parse about 25% faster. Across realistic documents, LiteParse processed pages at 2.8ms/page and 1.5× faster than the next-fastest local parser. LiteParse is open source and runs locally in Python, Node.js, Rust, or directly in the browser. Grab v2.14.6 → https://t.co/UJy6KQ1Dyi Bench Docs → https://t.co/rVY3Cxyj8H

Sep 22, 2026, 05:03 PM UTC

♡ 68 likes↻ 1 reposts↳ 12 replies

Visual Studio Code

@code

Formatting code is SO much easier with the Prettier extension ✨ #vscodeextensions #prettier https://t.co/ijZz9g0RyY

Sep 22, 2026, 02:01 PM UTC

♡ 300 likes↻ 28 reposts↳ 7 replies

OpenAI Developers

@OpenAIDevs

See how surgeon @pridgenmd uses Codex to build his own tools and review scientific literature on PubMed: https://t.co/i8cs5FikTw

Sep 22, 2026, 02:54 AM UTC

♡ 406 likes↻ 28 reposts↳ 29 replies

GitHub

@github

Just one engineer and a team of agents ported the GitHub Copilot agent runtime to Rust, shipping 800,000 lines of production code while retaining code quality. 🚀 How it worked 👇 https://t.co/wJ5qWMuGvV

Sep 21, 2026, 06:32 PM UTC

♡ 4.3K likes↻ 298 reposts↳ 192 replies

Vercel

@vercel

Build with Grok 4.7 and Vercel for less. 40% off until September 27th on AI Gateway. Try with @v0, @eve, and fx. https://t.co/mYLO5Gesx6

Sep 21, 2026, 11:19 PM UTC

♡ 420 likes↻ 34 reposts↳ 50 replies

swyx

@swyx

@latentspacepod @allenpark out now wherever fine podcasts are sold! (email, apple podcasts, youtube) https://t.co/AMwZCJ5IEK

Sep 21, 2026, 10:16 PM UTC

♡ 12 likes↻ 0 reposts↳ 13 replies

Cognition

@cognition

On FrontierCode 1.1, our benchmark for real-world engineering tasks, Grok 4.7 scores slightly below Grok 4.6. While strong on many hard tasks, it tends to over scope on others, leading it to trail behind Grok 4.6 in the aggregate. Read more: https://t.co/PgginMwMNp

Sep 21, 2026, 09:27 PM UTC

♡ 47 likes↻ 5 reposts↳ 6 replies

Cognition

@cognition

Try out today in Devin CLI and Devin Desktop: https://t.co/y3humFLPXs

Sep 21, 2026, 09:27 PM UTC

♡ 12 likes↻ 1 reposts↳ 1 replies

Cognition

@cognition

Grok 4.7 is now available in Devin. On FrontierCode 1.1, Grok 4.7 scores 59.4% on Extended. In our evaluation, we see the model performs very well on hard backend engineering tasks. https://t.co/qbliTyU1Dt

Sep 21, 2026, 09:27 PM UTC

♡ 579 likes↻ 38 reposts↳ 46 replies

Visual Studio Code

@code

🤖 Agent-First Development From our VS Code Learn library, check out this in-depth tutorial. @madebygps demos how to work effectively with AI agents in VS Code, covering agent workflows, governance, debugging, execution environments, and hands-on application development. ▶️ https://t.co/TRFobFfE5G

Sep 21, 2026, 08:45 PM UTC

♡ 230 likes↻ 30 reposts↳ 16 replies

Cognition

@cognition

To celebrate, we’re making SWE-2 free in Devin Cloud until October 8. Try it out today: https://t.co/2E11Z4BEYE

Sep 21, 2026, 06:34 PM UTC

♡ 39 likes↻ 3 reposts↳ 1 replies

Cognition

@cognition

With devin ssh, you can remote into Devin’s developer environment and use it as your own. Explore and edit code directly, launch dev servers and forward ports to test Devin’s work, or scp files back from the VM to you. And when you’re done, you can /handoff back to your machine using the CLI.

Sep 21, 2026, 06:34 PM UTC

♡ 38 likes↻ 1 reposts↳ 3 replies

Cognition

@cognition

Introducing Devin Cloud in Terminal and devin ssh: two new ways to use Devin's computer. Create, steer, and resume Devin Cloud sessions right in your CLI with /cloud. And for the first time, SSH into Devin's dedicated VM, then /handoff the work back to your own device.

Sep 21, 2026, 06:34 PM UTC

♡ 618 likes↻ 55 reposts↳ 53 replies

LlamaIndex 🦙

@llama_index

Grounded Confidence is here for Extract! 🦙 When your agents and workflows depend on extracted data, you need to know how accurate that data is. We’ve added confidence scores to give you a better read on extraction accuracy, field by field. Use them to decide which results your app can accept automatically and which need human review. Available on Cost Effective, Agentic, and Agentic Plus. Try it out on your docs -> https://t.co/v28mAfRAet

Sep 21, 2026, 05:03 PM UTC

♡ 40 likes↻ 2 reposts↳ 10 replies

Cognition

@cognition

Welcome @bcamhi to Cognition.

Sep 21, 2026, 04:59 PM UTC

♡ 118 likes↻ 5 reposts↳ 6 replies