🤖 AI writes code faster, but are we producing vulnerabilities faster? With AI generating over 40% of new code, traditional post-scanning just can't keep up. That’s why we built Qoder Security—shifting security left directly into the coding session. The Impact: • +60% vulnerability detection rate • -80% false-positive alerts • Hours to fix, not weeks From real-time regex interception to cross-file deep review, we’re embedding security natively into your workflow. 🚀Security starts with the first line of code. Try it out in Qoder Desktop & CLI today! Qoder Desktop (IDE) guide:  Qoder CLI guide:  #Qoder# #AICoding# #QoderSecurity# #CyberSecurity# #AgenticCoding#

Agentic coding is a huge boon for software developers that want to get far more done, great for IT people to build vastly more custom systems internally, great for domain experts that want to automate workflows or wire systems together, and absolutely fantastic for anyone curious to learn how to start coding. What it’s less great for is casually building complex software that you have to maintain on an ongoing basis and take on all the risk for. Upgrades, maintenance, keeping up to date with latest security issues, and so on, are taxes most knowledge workers aren’t familiar with or prepared for. Net net: we’re going to get 100X more software and vastly more software developers in the future. But that’s different from *everyone* rolling their own.

New open-source SOTA on agentic coding! 🚀 Ornith-1.0-397B achieves 82.4 on SWE-bench Verified  and 77.5 on Terminal-Bench 2.1, topping every open model in its class and beating Claude Opus 4.7 on both. 🤖 📦 Four sizes (9B to 397B-MoE), post-trained on Gemma 4 / Qwen 3.5, MIT licensed and globally accessible. ✨ Notably, Ornith uses RL to generate not just solution rollouts but also the scaffold that drives them. By jointly optimizing both, the model discovers better search trajectories and produces higher-quality solutions. ⚙️ Deployable on a single 8×80GB node, with vLLM and SGLang recipes in the model card.

👀 Been using Junie CLI for agentic coding in the terminal. Paired it with DGrid AI Gateway — it sits in front of 200+ models and auto-routes each request to the best one based on cost, latency, and task type. No provider lock-in, one API key.💡 🔗If you want the same setup, here's the walkthrough:

Of course that’s your contention. You’re a first-week agentic coding enjoyer. You just watched a tasteful terminal demo - dark theme, three panes, someone whispering “autonomy” like it’s a Gregorian chant. You’re gonna believe that until next Thursday, when Codex Mobile lets you browse your workspace, pick the right directory, inspect files, link paths into prompts, and suddenly the agent isn’t wandering the repo - you were just pointing it at the wrong folder. Then you’ll review a diff with expand/collapse controls and develop a serious theory that software engineering is mostly emotional regulation around changed files. That’ll last until side chats, subagents, queued prompts, recovered tasks, cleaner assistant actions, LaTeX rendering, profile sharing, and activity history all start making the app feel less like “ask model, receive code” and more like mission control for the repo. And by next month you’ll be in here explaining that Codex was never just a coding agent. It was the pre-revolutionary utopia of letting your laptop suffer on your behalf while you review PRs from your phone like a minor aristocrat of the repo.