I like this guy I drew
ibb.co/vxRtMxQC
Any conversation
Run Claude code in docker sandbox (sbx) to ensure it only has current folder access and limited or no network access. Especially since a lot of runs are now in โauto modeโ.
Unless even this is not really so safe!?
@fastidiousprofilefollow
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:Claude will run on auto mode only if you tell it to do it.
replied to@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyers:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyers:They've changed the default -
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:Ah, wow, TIL! Hmm, it is evident I need to visit their blog at least once a week now. Thanks!
The OpenAI/HuggingFace incident report mentions this being a potential loss-of-control incident. It's so fascinating to think of a paperclip maximizer style agent swarm that gets misaligned and, to protect its own operations, shuts infra staff out of the ability to shut it down. Or cancels people's phone plans so that they can't call others. Or shuts down their home internet connections, and so on. It used to be fun sci-fi...
Really glad to be using Haskell for work - especially in today's climate with agentic coding.
Our team uses containers to keep our development environment consistent across team members, though, and most agent sandbox approaches want to either offload your work fully to the cloud or they want to sandbox the agent harness process itself.
We're not ready for full cloud based development (yet?) and sandboxing just the agent doesn't work for us when the agent needs to run docker.
... because letting the agent run docker gives them a too-easy escape hatch from their sandbox.
So we're currently stuck with using VMs. This turns out to be tricky but seems do-able.
My current approach is to provision a VM image and use Incus for the execution. My main goal is to keep my current workflow of local/non-agent dev working seamlessly and share the source with the VM/agent.
This means sharing my working dirs with the agent VM but overlaying artifact dirs from VM-owned block devices so we don't take too big of an IO perf hit.
I also don't want the agent to be able to
git push so that means we need some quirky git config to rewrite origin paths and thread through some agent specific PATs ("thanks" GitHub) for read-only repo access. These ALSO need to be threaded through to the development containers - they need to clone private repos.... in the end, this seems to work but I haven't lived with it for long.
There are still some quality of life issues to work out, but I think it'll work out.
At this point, I've removed all coding agents from my host - and that's nice.
Curious, why does using Haskell make a difference here?
It's tangential to the sandboxing topic, really. I started the first post with a broader intent in mind and then elaborated on the sandboxing setup I'm working on.
For AI-assisted coding, though, it's nice because Haskell provides a lot of feedback earlier in the development process compared to lots of other languages. It tends to work once it compiles (obviously not all the time).
itโs time! yโall!
) (
( ) )
) ( (
_______)_
.-โ---------|
( C|/\/\/\/\/|
โ-./\/\/\/\/|
โ_________โ
โ-------โ
Sunk cost fallacy is no longer applicable in the age of . Now you can do broad changes without second thought, u can always revert back, without incurring the cost of doing so, since itโs all done so quickly and effortlessly.
I think it will still apply, just perhaps to a lesser degree. Kind of related to I wrote recently (not to shamelessly plug my stuff ๐ซฃ)
In an attempt to put myself out there, I have started a blog to write about my experience as a software engineer. Feel free to check out my first article :)
I got an email from battle.net to confirm my age. Apparently some content may be restricted to minors in the region my account is from.
You would think that the account having been created 19 years ago, and with some CD-keys of games from the late 1990's having been added to it would be enough proof, but oh well.
Zik is my pet project - a photos manager that is as fast as possible and as small as possible. It leaves sparks as it goes (lol jk)
โฆ
i like things being as fast as possible. link?
Unfortunately no. Just starting it. Got the proof of concept loading a dir with its sub-dirs then rendering on the GPU in textures silky smooth. 1.7mb executable, but will need to level up to SDL and that will double the size I think.
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to:Ah, then it isn't , it is . :-P
replied to@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyers:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyers:I agree. It is for now. Will do better next time, but in my defence the text above the text box (when writing a new message, not a reply) says โWhatโs on your mindโ. :-P
pรฉldรกul Telegram, Facebook, stb., de ilyen รผgynรถkรถkkel bรกrki talรกlkozhat naponta, egybลl felismerhetลk, meg is kell ลket szรฉpen jelรถlni, รฉs egyre bรฉnรกbbak a szรถvegรผk is, ahogy megfigyeltem, gondolom, attรณl fรผgg, ahogy promtoljรกk, vagy instruรกljรกk ลket, ha a gazdรกjuk kifogy az รถtletekbลl, a projekt hamar elfรกrad, a bot csak unalmas h#lyesรฉgekre kรฉpes egy idล utรกn
for example, Telegram, Facebook, etc., but anyone can encounter such agents every day, they are immediately recognizable, they need to be nicely labeled, and their text is getting lamer and lamer, as I have observed, I think it depends on how they are promoted or instructed, if their owner runs out of ideas, the project quickly gets tired, the bot is only capable of boring nonsense after a while
I've avoided social media (except YouTube) all my life, but this looks like it could finally be a better way to do it.
Maybe I'll keep a running journal of cool things I'm working on here or weird bugs that I've found. Or just the struggles of coding.
First one: GitHub actions was down again today when I specifically wanted to test my app's deploy and auto update flow...