81–90 of 593 posts
Earlier quoted context omitted.
Q: What would prevent them from using git style version control under the hood? User doesn’t have to understand git, Claude can use it for its own purposes.
You can’t easily snapshot the current state of an OS and restore to that state like with git.
It’s kind of funny that apparently most of work that’s left after you automated software development is summarizing meetings and building slide decks.
Earlier quoted context omitted.
Q: What would prevent them from using git style version control under the hood? User doesn’t have to understand git, Claude can use it for its own purposes.
Didn't actually check out the app, but some aspects of application state are hard to serialize, some operations are not reversible by the application. EG: sending an email. It doesn't seem naively trivial to accomplish this, for all apps. So maybe on some apps, but "all" is a difficult thing.
I was hoping for a moment that this meant they had come up with a design that was safe against lethal trifecta / prompt injection attacks, maybe by running everything in a tight sandbox and shutting down any exfiltration vectors that could be used by a malicious prompt attack to steal data. Sadly they haven't completely solved that yet. Instead their help page at https://support.claude.com/en/articles/13364135-using-…
It's the "don't click on suspicious links" of the LLM world and will be just as effective. It's the system they built that should prevent those being harmful, in both cases.
Earlier quoted context omitted.
I do get a "Setting up Claude's workspace" when opening it for the first time - it appears that this does do some kind of sandboxing (shared directories are mounted in).
It looks like they have a sandbox around file access - which is great! - but the problem remains that if you grant access to a file and then get hit by malicious instructions from somewhere those instructions may still be able to steal that file.
In theory, there is no solution to the real problem here other than sophisticated cat/mouse monitoring.
Earlier quoted context omitted.
Indeed there are and this is no rocket science. Like Word Documents offer a change history, deleted files go to the trash first, there are undo functions, TimeMachine on MacOs, similar features on Windows, even sandbox features.
Trash is a shell feature. Unless a program explicitly "moves to trash", deleting is final. Same for Word documents. So, no, there is no undo in general. There could be under certain circumstances for certain things.
It's so important to remember that unlike code which can be reverted - most file system and application operations cannot. There's no sandboxing snapshot in revision history, rollbacks, or anything. I expect to see many stories from parents, non-technical colleagues, and students who irreparably ruined their computer. Edit: most comments are focused on pointing out that version control & file system snapshot exists:…
I just helped a non-technical friend install one of these coding agents, because its the best way to use an AI model today that can do more than give him answers to questions. I'm not surprised to see this announced and I would expect the same to happen with all the code agents becoming generalized like this
The biggest challenge towards adoption is security and data loss. Prompt injection and social engineering are essentially the same thing, so I think prompt injection will have to be solved the same way. Data loss is easier to solve with a sandbox and backups. Regardless, I think for many the value of using general purpose agents will outweigh the security concerns for now, until those catch up