While working on openai/codex today, Codex surprised me by setting up its own heartbeat automation to poll my PR until CI was green and approvals were in. It kept checking every 10 minutes for an hour, merged the PR once everything was ready, then removed the automation. High
CODE
-
Securing Vibecoded Apps in 4 Steps with Replit
By
–
How to secure your vibecoded app in 4 steps Speed without security is a liability. Here's how to ship without leaving the back door open using Replit. Open thread ↓
-
Replit Security Agent Automates Code Vulnerability Detection
By
–
1. Run a Security Scan
— Replit ⠕ (@Replit) 28 mai 2026
Open Replit's Security pane and hit Run scan. The Agent audits your entire codebase to catch issues like SQL injection, XSS, and leaked credentials. Review the findings, accept the ones that matter, and they get sent straight to Agent for auto-fixes. Takes… pic.twitter.com/oH4gCpfIIk1. Run a Security Scan Open Replit's Security pane and hit Run scan. The Agent audits your entire codebase to catch issues like SQL injection, XSS, and leaked credentials. Review the findings, accept the ones that matter, and they get sent straight to Agent for auto-fixes. Takes
-
Claude Code Ships Dynamic Workflows for Complex Tasks
By
–
We also shipped dynamic workflows in Claude Code (research preview), for tasks too big for one pass. Make sure to default to auto mode so Claude isn't stopping for permissions. It's token-intensive, so save it for your biggest jobs: migrations, refactors, perf optimization,
-
Claude Dynamic Workflows Accelerate Code Migrations
By
–
Big migrations and refactors are some of a team's most important work, and the easiest to push off to a "better time" since they'd tie up engineers for a quarter. With dynamic workflows, Claude can now land that kind of work in days or weeks. More:
-
Claude Opus 4.8 Released: Stronger Coding Model with Benchmarks
By
–
Claude Opus 4.8 is out today. It's our strongest coding model yet: up on SWE-bench Pro (from 64.3 to 69.2) and noticeably more honest about its own work. It tells you when it's unsure and catches its own bugs instead of declaring victory early. Same price as 4.7.
-
Claude Opus 4.8 Now Available in Cursor with Performance Gains
By
–
Claude Opus 4.8 is now available in Cursor. On CursorBench, it's able to work much more efficiently than Opus 4.7. We've also found it to be more persistent on harder tasks.
-
Experimenting with Event Sourced Agent Runtime
By
–
experimenting with a new event sourced agent runtime that i made 🙂
-
RL Inference Stack Development in C for GB300 Hardware
By
–
Next will be writing the inference stack in C for simultaneous high-speed RL across a large block of GB300s. (We do use a little C++ tbh, but not much)
-
Vibe Coding: AI-Driven Rapid Development Trend
By
–
“Vibe coding” is quickly becoming one of the most talked-about AI trends in business and software development Instead of focusing purely on technical coding skills, vibe coding is about using AI tools to rapidly build, test and refine ideas through natural language prompts,