Curious (as a Claude Code user who is already sold on its power and capability) if you think that the Gemini CLI and/or the Codex CLI provide similar functionality and capability? i.e. is Claude Code special or first?
Also, thanks for sharing your setup details. Loved the pod you did with Dan Shipper. I've been wrestling with a parallel mobile access arrangement since before the episode but had trouble getting SSH to work with Max login creds (i.e. wasn't using the API key). Did you encounter anything similar?
Is your approach inherently secure because you are not getting it to process downloaded files, only text from Obsidian? I have been reading articles about prompt injection, malicious commands in PDF files and on webspages. Is there a risk that with file access, the AI can do some serious damage to your local machine?
Curious (as a Claude Code user who is already sold on its power and capability) if you think that the Gemini CLI and/or the Codex CLI provide similar functionality and capability? i.e. is Claude Code special or first?
Also, thanks for sharing your setup details. Loved the pod you did with Dan Shipper. I've been wrestling with a parallel mobile access arrangement since before the episode but had trouble getting SSH to work with Max login creds (i.e. wasn't using the API key). Did you encounter anything similar?
Is your approach inherently secure because you are not getting it to process downloaded files, only text from Obsidian? I have been reading articles about prompt injection, malicious commands in PDF files and on webspages. Is there a risk that with file access, the AI can do some serious damage to your local machine?