AI Coding & Agents

LangChain

@LangChain

At 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

Oct 16, 2026, 07:00 PM UTC

♡ 44 likes↻ 2 reposts↳ 3 replies

LlamaIndex 🦙

@llama_index

Doc 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 ->

Oct 16, 2026, 04:48 PM UTC

♡ 13 likes↻ 1 reposts↳ 8 replies

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

Oct 16, 2026, 08:12 PM UTC

♡ 24 likes↻ 1 reposts↳ 4 replies

GitHub

@github

New 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

Oct 16, 2026, 12:08 AM UTC

♡ 230 likes↻ 13 reposts↳ 17 replies

swyx

@swyx

@affaan @absurdistphil @aiDotEngineer full talk written up: https://t.co/EpmPzFAsgJ

Oct 16, 2026, 10:46 PM UTC

♡ 7 likes↻ 1 reposts↳ 0 replies

LangChain

@LangChain

When 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.

Oct 16, 2026, 05:00 PM UTC

♡ 3 likes↻ 1 reposts↳ 1 replies

LlamaIndex 🦙

@llama_index

Source: Table from Simon Ott et al., VL-DocIR, CC BY 4.0 (https://t.co/TUmK5MKeEg).

Oct 16, 2026, 04:48 PM UTC

♡ 4 likes↻ 0 reposts↳ 0 replies

LangChain

@LangChain

AI 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

Oct 16, 2026, 05:00 PM UTC

♡ 3 likes↻ 1 reposts↳ 0 replies

Cursor

@cursor_ai

Muse Wonder from Meta Superintelligence Labs is now available in Cursor! It scores 46.1% on CursorBench at default effort, the highest of any Muse model. Priced at $4/M input and $20/M output tokens. https://t.co/NGEnvB43LN

Oct 15, 2026, 10:56 PM UTC

♡ 2.2K likes↻ 100 reposts↳ 243 replies

Cognition

@cognition

Introducing Devin Oncall: Devin automatically investigates alerts and bugs, helping your team diagnose and resolve production incidents. Devin Oncall already handles thousands of alerts every day for some of the world’s largest companies. Let it become your SRE today. https://t.co/Nza88HwIKd

Oct 15, 2026, 05:49 PM UTC

♡ 945 likes↻ 80 reposts↳ 66 replies

OpenAI Developers

@OpenAIDevs

You can just build things with Codex We built a site for you to explore hardware projects from the community and share your own. https://t.co/zJQX1hXn2N

Oct 15, 2026, 10:08 PM UTC

♡ 1.3K likes↻ 90 reposts↳ 91 replies

Vercel

@vercel

Run your backend on Vercel. • Python is generally available • Containers for other runtimes & system libraries • Daemons for async jobs & background workers https://t.co/spPCQWUaWc https://t.co/H1lvSQE81d

Oct 15, 2026, 05:34 PM UTC

♡ 978 likes↻ 67 reposts↳ 55 replies

OpenAI Developers

@OpenAIDevs

Sites is now generally available for Enterprise, with US and EU data residency for new Sites in eligible workspaces. Build team apps with databases and authentication. @kagigz shows how to schedule updates and let teammates use their own connected data with Plugins in Sites: https://t.co/jYxRh5Pi2U

Oct 15, 2026, 08:39 PM UTC

♡ 633 likes↻ 38 reposts↳ 67 replies

Vercel

@vercel

Vercel Drives is generally available. You can now run stateful agents on Vercel. https://t.co/tbogIYouct https://t.co/etKyIfIQr4

Oct 15, 2026, 05:42 PM UTC

♡ 656 likes↻ 40 reposts↳ 52 replies

Vercel

@vercel

Introducing https://t.co/KWzuDDlyvD. Limited drops, original designs, and a few things you didn't see coming. Powered by @nextjs, @Shopify Hydrogen & @eve. https://t.co/RA6VsKRBRt

Oct 15, 2026, 07:02 PM UTC

♡ 632 likes↻ 30 reposts↳ 46 replies

Visual Studio Code

@code

✨ VS Code’s UI is evolving, shaped by developer feedback! Explore the modernized interface, with refined tabs, more consistent layouts, and new ways to customize your workspace. 🔗 Read the blog: https://t.co/grsqnjPFaD

Oct 15, 2026, 07:08 PM UTC

♡ 817 likes↻ 64 reposts↳ 36 replies

Vercel

@vercel

Ship SF 2026 is now live. Tune in: https://t.co/QLkcAa0gZF https://t.co/sGRiPvYplX

Oct 15, 2026, 05:18 PM UTC

♡ 478 likes↻ 24 reposts↳ 7 replies

Vercel

@vercel

https://t.co/ZeCq8gwrty

Oct 15, 2026, 04:59 PM UTC

♡ 200 likes↻ 21 reposts↳ 1 replies

Vercel

@vercel

The October 2026 AI Gateway Index is live. 1. Open weight ran over 70% of tokens, and took nearly 25% of spend, up 4x since June. https://t.co/kxHMurg7Sx https://t.co/f3Twn1GLwK

Oct 15, 2026, 06:41 PM UTC

♡ 99 likes↻ 8 reposts↳ 31 replies

Vercel

@vercel

Ship SF starts at 10am PT. On stage today: • Guillermo Rauch, CEO & Founder @Vercel • Tobias Lütke, CEO @Shopify • Diogo Almeida, CEO @typesafeai • Katelyn Lesse, Head of Engineering @AnthropicAI • Prashant Ratanchandani, VP of Eng @AIatMeta https://t.co/QLkcAa0gZF

Oct 15, 2026, 04:13 PM UTC

♡ 113 likes↻ 11 reposts↳ 12 replies