Congrats to the team on “The Limits of Long-Context Reasoning in Automated Bug Fixing” being accepted to ICLR 2026 The team put long-context reasoning to the test for automated bug fixing and found something surprising. Performance actually drops as context grows. Check out
CODE
-

DeepSeek V4 Pro Flash Day-0 vLLM Support Long-Context
By
–
Day-0 support for @deepseek_ai V4 Pro and Flash on vLLM — a new generation of DeepSeek model, purpose-built for tasks up to 1M tokens. Alongside the release, we're publishing a first-principles walkthrough of the new long-context attention and how we implemented it in vLLM. x.com/deepseek_ai/st…
-

DeepSeek V4 Launch with SGLang Optimizations and RL Pipeline
By
–
DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL training pipeline in Miles (by @radixark) for V4 at launch: Native "ShadowRadix" Design: DeepSeek V4's
-
Cursor 3.2 Releases New Agents Window Features
By
–
Download Cursor 3.2 to try these new features in the agents window:
-

Improved Worktrees Enable Parallel Task Execution Across Branches
By
–
Another way to parallelize work is with new and improved worktrees in the agents window.
— Cursor (@cursor_ai) 24 avril 2026
Run isolated tasks in the background across different branches. When you're ready to test changes, move any branch into your local foreground with one click. pic.twitter.com/h8H0Uc643YAnother way to parallelize work is with new and improved worktrees in the agents window. Run isolated tasks in the background across different branches. When you're ready to test changes, move any branch into your local foreground with one click.
-
Multi-root workspaces enable cross-repo agent sessions
By
–
We've also added multi-root workspaces for cross-repo changes.
— Cursor (@cursor_ai) 24 avril 2026
A single agent session can now target a reusable workspace made of multiple folders. pic.twitter.com/VPiwdqAFigWe've also added multi-root workspaces for cross-repo changes. A single agent session can now target a reusable workspace made of multiple folders.
-

Cursor 3 Introduces Multitask Async Subagents Feature
By
–
Introducing /multitask in the new Cursor 3 interface.
— Cursor (@cursor_ai) 24 avril 2026
Cursor can now run async subagents to parallelize your requests instead of adding them to the queue.
For already queued messages, you can ask Cursor to multitask on them instead of waiting for the current run to finish. pic.twitter.com/gtvOlup2hXIntroducing /multitask in the new Cursor 3 interface. Cursor can now run async subagents to parallelize your requests instead of adding them to the queue. For already queued messages, you can ask Cursor to multitask on them instead of waiting for the current run to finish.
-
Images 2.0 Enhances Codex Artifact Creation and Explanation
By
–
images 2.0 makes codex far better at creating and explaining artifacts: https://t.co/LadvjWH078
— Greg Brockman (@gdb) 24 avril 2026images 2.0 makes codex far better at creating and explaining artifacts:
-
Chronicle Enhances AI Agent Memory and Context Understanding
By
–
chronicle gives codex rich context and recent memory over what you’re doing: https://
x.com/OpenAIDevs/sta
tus/20462882437680826994/
… -
Open Source Code Execution Chat ML Innovation
By
–
Will play around! Open source execution over chat is what ML work has been waiting on.