Separately, we’ve also heard reports of issues with Opus 4.7 in Claude Code. The team is working on those and we’ll share more as we roll out improvements over the coming days.
CODE
-
Claude Code Quality Issues: Post-Mortem Analysis Published
By
–
We’ve been looking into recent reports around Claude Code quality issues, and just published a post-mortem on what we found.
-
GPT-5.5 Spud Launches: Major Leap in Coding and AI
By
–
BREAKING:
— Dan Shipper 📧 (@danshipper) 23 avril 2026
GPT-5.5 "Spud" is out and it is a BEAST
We've been testing it @every for the last 3 weeks on everything from coding, to writing, to knowledge work. Here's our day 0 vibe check:
– It's a step change in coding AND it's easy to talk to. It's fast and friendly and… pic.twitter.com/lMl2wdwADbBREAKING: GPT-5.5 "Spud" is out and it is a BEAST We've been testing it @every for the last 3 weeks on everything from coding, to writing, to knowledge work. Here's our day 0 vibe check: – It's a step change in coding AND it's easy to talk to. It's fast and friendly and
-
Multi-Agent Orchestration Patterns in Agent Development Kit
By
–
From Agents Skills to Systems: 5 Multi-Agent Orchestration Patterns in ADK 2.0 Check out my new article with @addyosmani covering how developers can build Multi-agent systems with Agent Development Kit 2.0
-
LangSmith Fleet: Agents Now Create and Edit Files
By
–
New in LangSmith Fleet: Create and edit files with your agent.
— LangChain (@LangChain) 23 avril 2026
Your agent can now work with files directly. Create documents, presentations, and webpages inside a conversation, or upload your own files and edit them together.
📄 Work with images, PDFs, and text files.
💬 Build… pic.twitter.com/FN1MJGh4yiNew in LangSmith Fleet: Create and edit files with your agent. Your agent can now work with files directly. Create documents, presentations, and webpages inside a conversation, or upload your own files and edit them together. Work with images, PDFs, and text files.
Build -
OpenClaw: Open Source Self-Hosted AI Agent Management Platform
By
–
– Supports any model
— Robert Scoble (@Scobleizer) 23 avril 2026
– Self-hosted deployment, as low as €4/month
– Per-session sandbox environment
– Credential isolation
– Fully observable subagent (delegation)
It is MIT-licensed and open source. Give it a star on GitHub.
Link: https://t.co/kuQU56K2Yc https://t.co/wrk0Zl0w6F– Supports any model
– Self-hosted deployment, as low as €4/month
– Per-session sandbox environment
– Credential isolation
– Fully observable subagent (delegation) It is MIT-licensed and open source. Give it a star on GitHub. Link:
https://
github.com/stainlu/opencl
aw-managed-agents
… -
Creative Strategist Kamau Builds Ideas Fast with Replit
By
–
Supporting people with a vision who want to build something from the ground up.
— Replit ⠕ (@Replit) 23 avril 2026
Join Kamau – creative strategist – in building ideas fast with the power of Replit. pic.twitter.com/7MY9mlnRGOSupporting people with a vision who want to build something from the ground up. Join Kamau – creative strategist – in building ideas fast with the power of Replit.
-
Configure Any AI Model Before Official Support Launch
By
–
you can configure any model. support will come once it's out officially.
-
Decoupled DiLoCo Training System Enables Resilient Large Scale AI
By
–
It's been a delight to provide small amounts of advice and suggestions to people working on the Decoupled DiLoCo training system. This approach enables graceful handling of failures in large scale training jobs, by allowing (N-1) / N units to proceed when one fails.
— Jeff Dean (@JeffDean) 23 avril 2026
Thread ⬇️ https://t.co/z97PgtNBuuIt's been a delight to provide small amounts of advice and suggestions to people working on the Decoupled DiLoCo training system. This approach enables graceful handling of failures in large scale training jobs, by allowing (N-1) / N units to proceed when one fails. Thread
