51–60 of 334 posts
I think these styles of apps will be popular for OpenAI and Anthropic as they help solve some of their moat issues. The deeper you integrate someone's files into their app, the harder it will be to switch AIs
Earlier quoted context omitted.
I'm only familiar with the Anthropic equivalent, but the cognitive load is different as opposed to necessarily better or worse. I have friends who prefer mousing around the UI. Tabs for long-running often-compacted sessions is a difference I've noticed in emergent UX.
I use Claude Code CLI, Codex Cli. Both are really good, they don't eat memory like the GUI apps.
The best feeling has to be in the CLI, in my oppinion. A low-stakes project where you can let ultracode runaway from you in the CLI is the most fun.
This will make it much easier to trap people into installing it without any isolation just to their primary user account or even make it run with admin privileges by default. With the recent security related events we already see that it seems to be wide spread practice that many operators avoid the hassle of isolating their agents. It is just an incredible cultural experience to see how quick stupidity gets accepted…
The Linux version seems to use bubblewrap + seccomp for a "workspace sandbox" automatically, in addition to the auto mode and/or user approval. A VM would be even better, but people could presumably run this in one if we manage to convince them of higher sandboxing in general ?
When I tried that with the Codex CLI version on a Linux VM, I did not get it to work. Possibly because OpenAI only supports connecting ChatGPT to a desktop installation of Codex?
Does this mean it is possible to talk to Codex from ChatGPT on a mobile phone now? When I tried that with the Codex CLI version on a Linux VM, I did not get it to work. Possibly because OpenAI only supports connecting ChatGPT to a desktop installation of Codex?
Earlier quoted context omitted.
How do I get it to fix my Bluetooth if I do that? If you've been AI-pilled, 2026 is the year of Linux desktop because instead of dicking around with config files, I can just tell AI to fix python.
pi.dev, local model, (RAG-ed) copy of archwiki. You are more able than you believe. Already now, no permission needed.
Earlier quoted context omitted.
How do I get it to fix my Bluetooth if I do that? If you've been AI-pilled, 2026 is the year of Linux desktop because instead of dicking around with config files, I can just tell AI to fix python.
pi.dev, local model, (RAG-ed) copy of archwiki. You are more able than you believe. Already now, no permission needed.
Earlier quoted context omitted.
The Linux version seems to use bubblewrap + seccomp for a "workspace sandbox" automatically, in addition to the auto mode and/or user approval. A VM would be even better, but people could presumably run this in one if we manage to convince them of higher sandboxing in general ?
Bubblewrap gets a bit confused inside a Docker container. If anyone knows how to run Codex inside a Docker container on Linux without it constantly complaining about a broken bubblewrap, please tell.
Why would you even use bubblewrap once it's running in a container? I've been running Codex in a container since it was publicly available, not even sure what you'd use bubblewrap for when you already separated codex from the rest of your filesystem?
Earlier quoted context omitted.
How do I get it to fix my Bluetooth if I do that? If you've been AI-pilled, 2026 is the year of Linux desktop because instead of dicking around with config files, I can just tell AI to fix python.
pi.dev, local model, (RAG-ed) copy of archwiki. You are more able than you believe. Already now, no permission needed.
Also note, that RAG and even vector search are more paths of the early days that didn't prove too valuable. Just let your agent search it directly and optionally create an index as a default entrypoint for common topics.