well I just had a codex cloud worker fill it's own storage to max making it's VM become unresponsive
If I got a dollar every time I saw a post saying something like, ' What are vibe coder's going to do when they have to maintain a large code base after they just let the AI read the code?'
I could probably buy Spacex
I like Claude Code Projects so much that I got Opus 5.5 to investigate how Projects works for Claude Code Desktop. So I can make a ChatGPT Plugins Extension version of it. What do y'all think?
Good, I was waiting for something like this.
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉
We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly.
1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials.
The agent gets the task done, but it doesn’t get your passwords..
You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault.
➡️Learn more: bit.ly/487da6J
I am doing a stupid amount of PRS and local git work right now. Both Claude and Codex have resets that expire tomorrow and I'm just trying to use this stuff up
If you have or use ChatGPT's or Codex Dot agent. For the love of god, you need to do this. Because I know every single one of you has at one point or constantly have to deal with the Dot asking you for permission. And then rejecting you right after and then just refuse to do it.
Well FYI In case you didn't know which I'm sure you don't because I sure as fuck didn't. The ChatGPT Dot Can create a long standing rule when you've been having to constantly give it permission for stupid shit all the time.
I got a freebie reset. We all did for Claude that expires October 22nd so I'm going to have them blasting PRs all day so I can get that reset in and blast more PRs and local work out. 😂
Well that was pretty easy getting the Codex and Cursor cloud agents reviewing each other's work. The Dot sees all repos So when they make a PR he can review it automatically and they just know to wait and watch for his comments. He even does the Windows local QA for them.
This is major. If you don't know why, trust me. This is a big deal.








