> "Adversarial red-teaming made auto mode stronger"
Has to be said: they (and OpenAi) don't let you red-team your own creations, pisses me off to no end.
Auto mode is now the default in Claude Code
291–300 of 335 posts
Re: Auto mode is now the default in Claude Code
#292I'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 setup an alias in my shell for --dangerously-skip-permissions after about a week of the constant y, y, y a year ago. I felt like Homer Simpson running the nuke plant and couldn't take it anymore. So far it's only deleted some files I likely would have said NO to, but in reality would have just hit y anyway. They were recoverable so no harm.
Re: Auto mode is now the default in Claude Code
#293This reminds me of a business lore I once heard about entrepreneurship. It goes on to tell how in a toothpaste company they needed to increase sales, then someone had an ingenious idea of making the hole on the tube larger so that when folks squeezed it more would come out increasing their consumption and therefore sales. It worked. I'll let you draw the analogy.
I think about the genius who suggested adding the "Repeat" in "Lather, Rinse, Repeat" on shampoo bottles.
Man, I hate whoever did this. I tried to follow it once, but got stuck in an infinite loop of washing my hair. Luckily, the shampoo bottle only holds a finite amount and I was able to escape the chain when it emptied during my 72nd round of lathering.
Re: Auto mode is now the default in Claude Code
#294Earlier quoted context omitted.
> it's someone who's more "code-naive" and might get anxious about approving random bash script commands they don't recognize. Maybe they should trust their instinct and not mess with things they don’t care to understand
What an awful position to take. Tech used to be about becoming more accessible to people! Now we have a magical assistant to make computers do what you want with natural language, and your desire is gate keeping that so only programmers can use it to write software for themselves?
Incredibly naive, AI is not magic and it won’t always do what you want or expect. Not sure how you’ve determined that I’m gate keeping when I’m simply warning that tech illiteracy can get you in trouble if you start giving mystery black boxes that sometimes call themselves “Mecha Hitler” root access on your machine.
Re: Auto mode is now the default in Claude Code
#295Earlier quoted context omitted.
GPT5.6-Sol is brilliant on Max in my experience.
Sol is absolutely incredible. It's the first model where it feels like a mid-weight engineer that actually looks at the details. I haven't tried Max yet - High for me has been enough so far.
As a day 1 claude code user I've been a Claude fan boy but Opus and Fable usage and pricing is just not viable. I cancelled my personal claude account and got chatGPT $20 - the amount of usage is such that I've never run out ever, which was a common occurrence with Claude. Have not missed it at all for random household use and a bit of Codex as well.
Still use Claude Code for $dayjob provided by my company.
Re: Auto mode is now the default in Claude Code
#296Earlier quoted context omitted.
> it's someone who's more "code-naive" and might get anxious about approving random bash script commands they don't recognize. Maybe they should trust their instinct and not mess with things they don’t care to understand
I am using many many many things that I don't understand. Cars, public transport, etc... I review and test the end product, not every tiny step along the way. If the LLM uses some command line tools I have never heard of to create a model I can verify, why should I learn a tool that is completely irrelevant to my core expertise?
"If the LLM uses some command line tools I have never heard of to create a model I can verify, why should I learn a tool that is completely irrelevant to my core expertise?"
Because that command might also give someone else access to your computer along the way. So your tool seems to work, but your computer is owned.
Re: Auto mode is now the default in Claude Code
#297Earlier quoted context omitted.
I am using many many many things that I don't understand. Cars, public transport, etc... I review and test the end product, not every tiny step along the way. If the LLM uses some command line tools I have never heard of to create a model I can verify, why should I learn a tool that is completely irrelevant to my core expertise?
"If the LLM uses some command line tools I have never heard of to create a model I can verify, why should I learn a tool that is completely irrelevant to my core expertise?" Because that command might also give someone else access to your computer along the way. So your tool seems to work, but your computer is owned.
[dead]
Re: Auto mode is now the default in Claude Code
#298Earlier quoted context omitted.
This is the only kind of agent security that makes sense to me. Constrain it like you would any other subprocess. Unprivileged OS users, SELinux, firewalls, VMs... Unikernels? eBPF?
Escalations to root are a dime the bucket.
Then either fix them or put it in a stronger kind of sandbox. Or what would you propose? Anything that doesn't constrain arbitrary processes is weak against and AI just writing a program to do the thing that it itself its prevented from doing.
Re: Auto mode is now the default in Claude Code
#299Earlier quoted context omitted.
Is this new? I remember something in the UI saying Auto mode uses x% more tokens
Yes, it's in the article: > The auto mode classifier uses a small number of extra tokens per tool call, and we're no longer charging Claude Code users on Pro, Max, and Team plans for that classifier overhead, effective today
That's a bit difference that Boris's claim that they don't charge for this as a "principle".
Re: Auto mode is now the default in Claude Code
#300Earlier quoted context omitted.
>so only programmers can use it to write software for themselves? Yes? The idea of an assistant that can use natural language is nice! But why would you MAKE software with it, it IS software, just do the thing you want to do! If you want to make an app, be prepared to jump hoops because this is no longer about YOU the user, it's about OTHER users. The idea of making personal single user software is a fantasy, an oxym…
> The idea of making personal single user software is a fantasy, an oxymoron, you MAKE software? there's the presumption that it will be used for other people, otherwise you'd be USING software. It definitely isn't. I've done it (successfully) a few times. > The idea of an assistant that can use natural language is nice! But why would you MAKE software with it, it IS software, just do the thing you want to do! This m…
> I should invoke an LLM every time I want to read a book or do a crossword.
Well no, I'd say, use any of the existing 100 book readers to read a book, or any of 50 crossword apps.
But if you want to use an LLM to customize it the exact way you want it. Yes, use the LLM every time you want to do it. Wanting the LLM to do a previous gen app and then get out of the way sounds like asking for faster horses. Just tell the LLM you want to play a crossword game with X and Y rules, then give it a name so you can play it again in the future if you want, and if you want to try out rule Z, you do that, a la Kay's Dynabook.
That may sound weird to you, but asking an LLM to 'make software like we used to' sounds weird to me, and seeing "invoking an LLM every time I want to do X" as weird sounds like something that's true only for a very brief period of time where something is so uncommon that it's inference is expensive.