Stop prompting your coding agents.
The people building Claude Code and Codex don't prompt anymore — they design loops. New video: what loop engineering actually is, the 5 building blocks, and the 2 traps that burn your token budget. https://
youtu.be/NjXIIH9vcv0
CODE
-
Stop prompting coding agents, design loops instead – loop engineering
By
–
-
Cursor’s design mode enhances MagicPath creations
By
–
There are also a few Cursor-only things that are really cool. For example, you can use Cursor's very own design mode to work with MagicPath creations.
— Pietro Schirano (@skirano) 10 juin 2026
It's pretty cool! pic.twitter.com/smffWLajpkThere are also a few Cursor-only things that are really cool. For example, you can use Cursor's very own design mode to work with MagicPath creations. It's pretty cool!
-
LangSmith Fleet template: Software Engineer coding agent from Slack, Linear, GitHub
By
–
LangSmith Fleet template spotlight: Software Engineer Ships code from Slack, Linear, and GitHub in a sandbox A coding agent that takes issues from @Linear
, writes and verifies the code, and opens a PR. Triggered directly from Slack. -
Full-text search JSON filtering with custom inverted index for SmithDB
By
–
How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latency of 400ms? Here’s an inside look at how we built a custom inverted index from scratch for SmithDB.
-
Asking for the wildest thing built with Codex
By
–
what’s the wildest thing you built with codex so far?
-
Cursor’s code review agent faster, cheaper, and finds more bugs
By
–
Cursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs.
— Cursor (@cursor_ai) 10 juin 2026
You can also use /review to run Bugbot locally to catch and fix issues before pushing code. pic.twitter.com/Pl7lhoR6TECursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs. You can also use /review to run Bugbot locally to catch and fix issues before pushing code.
-
Parallax: Local Linear Attention matches FA 2/3 when using Muon
By
–
Parallax is a parametrized form of Local Linear Attention that drops the numerical solvers and matches FA 2/3 on decode. The most impressive part is that the architecture's benefit works with Muon but disappears under AdamW because the model learns to suppress it. It's
-
RubricMiddleware: defining the ‘done’ state for agents
By
–
IN CASE YOU MISSED IT: We added RubricMiddleware to Deep Agents. RubricMiddleware is the way to tell the agent what 'done' looks like — and to keep it going until it gets there.
-
Physical AI: sensor data et vision dans les robots
By
–
Physical AI fuses real-time sensor data, computer vision, and machine learning algorithms directly into robotic platforms, giving machines the ability to perceive and respond to their surroundings rather than following pre-programmed paths. #IIoT #PhysicalAI #ComputerVision pic.twitter.com/N6564oqstB
— Lucian Fogoros (@fogoros) 10 juin 2026Physical AI fuses real-time sensor data, computer vision, and machine learning algorithms directly into robotic platforms, giving machines the ability to perceive and respond to their surroundings rather than following pre-programmed paths. #IIoT #PhysicalAI #ComputerVision
