I really tried to make antigravity cli work. I got AI ultra, paired it with Fable, ran it standalone, and I just have no fucking idea what the use case is for this shit.
Getting YouTube and Google health premium with it is super dope but damn…frustrated as hell.
@EvenRealities what are the chances of us getting keyboard support for terminal mode? Thinking about building an app but no point if you got it cooking 🤔
Introducing Claude Science, a new app designed with every stage of research in mind.
Artifacts traced to their code, environments managed on demand, and 60+ optional scientific databases that you can connect.
Available now in beta.
Claude code currently unusable with inference profiles. Extremely slow, and my work place is now on fire, back to coding with my brain like the old days 😭
Claude Code Desktop now supports --dangerously-skip-permissions!
This skips all permission prompts so Claude can operate fully autonomously. Great for workflows in a trusted environment where you want no interruptions, no approval prompts, just uninterrupted work.
But as the name suggests... use it with caution! 🙏
@amorriscode@trq212 @adEvvn Also being able to ssh into my own environment would be a nice to have and I just wouldn’t need Termius at all at that point.
@trq212 @adEvvn @amorriscode It would be dope if it was close to feature parity with the TUI. It’s odd making all of these optimized workflows and not being able to use any of them with the app. It’d be a hard sell getting me to put down TUI + SSH for this. So much potential though.
Definitely the buggiest Claude Code release I’ve experienced so far. Jealous of everyone that can get the teams feature working with bedrock and telemetry enabled. 😭
@CodeAkram@rudrank@amorriscode I usually get flickering if my conversation is too long AND my todo list is open. If closing the todo list doesn’t help or it’s not applicable, I just open and close my keyboard. (I’m using TMUX + Termius on iOS)
This is what I’ve been using since they rolled out the plan subagent. You create a hook that injects one line into each agent that simply tells it to read the plan and update it with progress upon completion. It should FEEL the same as Claude md without context rot. Also this is by no means the best way to do this, just A way of doing it. 😬