I ve been using a lot of AI-generated code lately, and while it definitely speeds things up, security feels like a weak spot.

I ve run into issues like missing auth, exposed endpoints, and weak configs stuff that AI doesn t really flag unless you explicitly ask.

Curious how others are handling this:

• Do you rely more on manual reviews or tools?

• Any workflows that consistently catch vulnerabilities?

• Have you faced any real incidents because of AI-generated code?

Hey everyone - quick update on DeployHermes (managed hosting for Hermes agents on Fly.io).

Since our last public release (right after we moved the stack to Vercel), we ve been heads-down on reliability and on features people actually asked for. Here s what s new:

Hey everyone,

I made this extension for myself because long chats in ChatGPT and Gemini kept getting slow and annoying to work with.

At first I just wanted to make long AI chats easier to handle, but then I added export too, because I often need to move information from one chat to another or save useful chats somewhere else.

Now it can:

The main update : single-window multi-project.

All your projects now live in the sidebar, switch in one click, no new windows. The sidebar has been fully reworked : project switcher, task threads by status (todo/in-progress/review), drag-and-drop reordering, pinned chats, collapse all.

Also in 1.2.0 :
Sequential execution for direct tasks (no more two tasks on the same branch)
Kanban bar chart showing task count per column
Task queue number visible in the sidebar
Documentation accessible directly from the sidebar
Pin chats, rename chats, reset button in task creation

Update via Settings Check for Updates or download at coddo.ai

I just shipped a new Command Palette in Room Service.