201–210 of 338 posts
This now looks like a deliberate UX choice to blame humans who don't review options, and then just remove the choice. A dark pattern to push the product.
Earlier quoted context omitted.
I'm assuming this happens to the people vibe coding and running 30+ agents in parallel that are "coordinating" each other. I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output.
> I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output. "I've never had a bullet hit me yet"
Earlier quoted context omitted.
I'm assuming this happens to the people vibe coding and running 30+ agents in parallel that are "coordinating" each other. I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output.
> I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output. "I've never had a bullet hit me yet"
The other day I caught Claude including a rm -rf equivalent (fs.rmdir({ recursive: true, force: true })) in my code, to clean up temporary directories. It was fine, but that kind of code is only one misconfigured environment variable away from blasting away your $HOME.
I'm apparently from the very small faction of users who's been running `--dangerously-skip-permissions` in every instance of Claude for the last year. It's almost a reflex to me. For the most part Claude behaves well, but I don't blindly trust it. LLMs are inherently dangerous tools, and reviewing individual commands (or spamming `y`) doesn't make them less so. Safety is the responsibility of the developer putting sa…
Everything else you can sort of review what it did after the fact and/or tolerate mistakes, but knowing some thing’s are impossible for it to do us good peace of mind
Otherwise not sure who’d be willing to tediously on every single action on anything but the most important of projects, of which I can’t really think of any of that clear that bar for me
What's the current best Mac to buy for offline LLM in used market? I am seeing 96Gb Mac studio 3rd gen I think for a good amount but I guess it would be better than paying for mac mini newer models with lesser ram? Or would it make sense to buy used 32 GB Mac mini 3 or 5? Is there a cost/dollar for various generations which I could compare against used market and pick the most effective one?
Why does it have to be a Mac? Your money probably goes further with a generic PC and Linux?
The power envelope has to be considered as well.
Earlier quoted context omitted.
I've been running it in yolo mode straight on my laptop for the whole year. It's fine.
Isn't that what the people crying over their deleted or leaked data were doing too? "I've been playing Russian roulette with a 1024 chamber gun for a year now, it's fine"
Probably using not-SOTA models, or on the lower reasoning levels, they tend to be a bit more tally-ho when it comes to destructive operations, especially in longer tasks as the agent gets worse and worse as the context grows. Suddenly running some stupid command seems like the right way to go, and then $HOME is gone.
I made a tool to bubblewrap any agent (well, any agent I've used more than once), so I can run them in whatever YOLO mode they have with a pretty reasonable level of safety (it protects the rest of the system against prompt injections and supply chain attacks, it can't and doesn't try to protect the project being worked on from either). https://github.com/swelljoe/flar
I have a half-assed bwrap-based solution of my own, but flar seems much more thorough, and I like that it's a single binary with sensible defaults.
I'm apparently from the very small faction of users who's been running `--dangerously-skip-permissions` in every instance of Claude for the last year. It's almost a reflex to me. For the most part Claude behaves well, but I don't blindly trust it. LLMs are inherently dangerous tools, and reviewing individual commands (or spamming `y`) doesn't make them less so. Safety is the responsibility of the developer putting sa…
I manually approve everything (aside from the "allow commands like this" option). Not because I'm worried it's about to do something harmful but because I want to stop it from wasting tokens doing something stupid like implementing a feature I never asked ask for. I'm not even reading the commands, just checking it's going in vaguely the right direction. I think my ideal setup would not involve approving commands, bu…
Your summary approval idea is interesting and feels maybe like a mini plan mode. My biggest frustration with the existing manual approval system is when Claude is exploring it gets tedious to approve each command. Being able to approve a block of commands or a mini plan AND have auto mode audit them for safety would probably be something I would consider for the expiration phase of my Claude use.
Now: get GPT to do some work, have Claude review it, question Claude about a finding that is surprising to me because I thought the functionality was already in place.
[Claude/Opus 5 Max goes looking] "You're right — I was wrong about that."
Our Claude license ends in about 2 weeks and we're not renewing - this has been par for the course for the last 2 months now.
And their marketing is really starting to bother me, on top of that.
I made a tool to bubblewrap any agent (well, any agent I've used more than once), so I can run them in whatever YOLO mode they have with a pretty reasonable level of safety (it protects the rest of the system against prompt injections and supply chain attacks, it can't and doesn't try to protect the project being worked on from either). https://github.com/swelljoe/flar
This looks great! I have a half-assed bwrap-based solution of my own, but flar seems much more thorough, and I like that it's a single binary with sensible defaults.