That is not my experience.
Claude Code runs Git reset –hard origin/main against project repo every 10 mins
21–30 of 219 posts
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#22tbf, that's claude's workspace
do not share a workspace with the llm, or with anybody for that matter.
How would the llm even distinguish what was wrote by them and what was written by you ?
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#23Earlier quoted context omitted.
That's not how the systems work. Just by a thing being common in training data doesn't mean it will be produced. > I guess, what I'm trying to say ... is this even a bug? Sounds like the model is doing exactly what it is designed to do. False, it goes against the RL/HF and other post training goals.
> Just by a thing being common in training data doesn't mean it will be produced. That's not what I said at all. I never said it will be produced. I said there is some probability of it being produced. > False, it goes against the RL/HF and other post training goals. It is correct that frequency in training data alone does not determine outputs, and that post-training (RLHF, policies, etc.) is meant to steer the mode…
It is meaningless to say that because the author was able to reproduce it multiple times.
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#24Not sure I understand, wouldn't permissions prevent this? The user runs with `--dangerously-skip-permissions` so they can expect wild behaviour. They should run with permissions and a ruleset.
The rules and permissions are no longer program flags, but plain text for the agent to "obey".
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#25Earlier quoted context omitted.
I was thinking surely scheduled tasks need to be explicitly invoked but nope: https://code.claude.com/docs/en/scheduled-tasks#set-a-one-ti... Some people are upset at my brave new world characterization, but yeah even as someone deriving value from Claude Code we've jumped the shark on AI in development. Either the industry will face that reality and recalibrate, or in 20 years we're going to look back on these days…
Feels like just yesterday that everyone agreed that critical code is read orders of magnitude more than written, so optimizing for quick writing is wrong.
Genuinely I think that perspective is still shared by many/most engineers.
I think we’ve seen a wave of bad actors - either employees of LLM companies, or bots - pushing the idea hard of code quality not mattering and “the models will improve so fast that your code quality degrading doesn’t matter”.
I think the humans pushing that idea may even believe it, but I don’t think they’re usually employed as software engineers at regular non-AI companies, rather they have some incentive to believe it and convince others as well
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#26Earlier quoted context omitted.
I was thinking surely scheduled tasks need to be explicitly invoked but nope: https://code.claude.com/docs/en/scheduled-tasks#set-a-one-ti... Some people are upset at my brave new world characterization, but yeah even as someone deriving value from Claude Code we've jumped the shark on AI in development. Either the industry will face that reality and recalibrate, or in 20 years we're going to look back on these days…
People aren't upset about your characterization. Catch phrases, memes, or other low qualitative comments (with no context, elaboration or personal angle) are contrary to community ethos and down voted.
This would be a more substantive comment if you also addressed the topic at hand as I did, rather than regurgitating the rules of the site.
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#27I'm curious how common this is or if this just affects this one user.
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#28Hope they don’t auto-close this one in two weeks
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#29cool. if you choose to use a non-deterministic black box of bullshit, should you really be surprised when it shits all over your floor?
the purpose of a system is what it does!
Re: Claude Code runs Git reset –hard origin/main against project repo every 10 mins
#30Prompt injection?
I was thinking surely scheduled tasks need to be explicitly invoked but nope: https://code.claude.com/docs/en/scheduled-tasks#set-a-one-ti... Some people are upset at my brave new world characterization, but yeah even as someone deriving value from Claude Code we've jumped the shark on AI in development. Either the industry will face that reality and recalibrate, or in 20 years we're going to look back on these days…
I agree that it's worrying that we're moving more and more towards implicit and opaque state. Hiding what exactly is getting edited, very limited tooling to check what the subagents are doing exactly, setting up scheduled and recurring tasks without it being obvious etc.
It's tending more and more towards pushing the user to treat the whole thing as a pure chat interface magic black box, instead of a rich dashboard that allows you to keep precise track of what's going on and giving you affordances to intervene. So less a tool view and more magic agent, where the user is not supposed to even think about what the thing is even doing. Just trust the process. If you want to know what it did, just ask it. If you want to know if it deleted all the files, just ask it in the chat. Or don't. Caring about files is old school. Just care about the chat messages it sends you.