After I've received a comment about that my writing style sounds like AI generated text, I decided that I want to sound differently when I communicate with others.
Applying the logic of reading AI generated text leads to human imitating that dialect, I can also teach myself a different form of writing by writing an agent skill that transforms the model's text output.
So here it is, a Shakespeare skill that makes your agents sound like an Early Modern English play.
#lifehack (well, sort of, to be verified in the future)
I took this comment as advice to go outside and touch some grass :D
Maybe I am using agentic environments a little too much lately? In the case of the weblog articles I wrote everything myself first and let the agents check against missed formatting rules, so the LLM was e.g. adding the references section and cutting/pasting the overview section together.
I usually use agents for fact checking most though, so e.g. in my malware writeups that I wrote I let my agents fact check if (parts of) what I discovered was also confirmed by other parties that analyzed e.g. the same malware samples.
The wiki learning courses were written by me, then rewritten by my agents, that's why there's still lots of unicode stuff in there. The articles were from my old website, but I let agents rewrite them to fit the new (linted) document format.
I have to now proofread everything and change/rewrite them over the course of the next weeks or months, and have to do that incrementally because it was just soo much content.
That was kinda the point behind the posted article: How to get to a point where most of the gruntwork is automated so you'll only have to proofread afterwards.
Usually that still takes a long while, especially when it's exploit or hardware errata or memory errata related. Verification of binary exploits is not as automated yet as I want it to be, hence my other projects and experiments with eBPF etc.
I think the only possibility that comes to mind is creating an ebpf module that sandboxes all filesystem calls and trampolines all ld_open calls.
But then you would have to provide massive amounts of patched/"safe" variants of all kinds of shared libraries which is unfeasible.
But I mean in the xorg use case it would be possible to just provide your own library that fakes the expected returns and sends fake data to the sandboxed applications.
I did a similar thing with barrier (though using LD_PRELOAD, see [1]) on my debian system to force a different behavior.
Source: Am kind of experimenting with ebpf a lot for that use case. C ABIs and SO files are a mess though. A real messy mess.
I am asking because I maintain botnet ASNs that are spamming/phishing/scamming our customers, and this would be a nice complementary category for it.
Most often I realized that a lot of those "growth" companies have rotating ASNs that they go through after each larger spamming campaign. I'd assume they do the same thing in the admob/adclick world.
Built my own harness with much better sandboxing, because I am using abliterated models for the implementations and they sure try to escape out of their sandboxes. A lot.
The sandbox from other harnesses like e.g. OpenCode essentially is useless. They think parsing arguments alone to detect paths helps, and LLMs know that because they will just pipe data differently then to escape the path traversal checks. Happened a lot to me (and was the primary reason for my to write my own harness from scratch).
Thinking in filesystem access alone is also a futile attempt at sandboxing. A much better way to think about sandboxes is policies and capabilities, with temporary access for agent roles rather than sessions (or, well, forever).
I’ve been looking along a similar line, but I came at it from the infra side rather than the software.
Mine pretends to be a local ACP agent, but it’s actually managing a Docker container and proxying the ACP connection into the container over websocket. You can specify a bunch of utility stuff in the YAML definition like directories to bind-mount, directories to copy from the host, scripts to run when the container starts, etc. You can also toggle whether ACP-native tools like read/write file and shells execute on your host or in the container (in container by default).
Works well, I forget whether I’m on that or pi-ACP directly until it spits out a time in the wrong timezone or I forget that it can’t check my DNS settings or something.
Really cuts down on the damage it can do. Mine is basically down to “it can delete my ~/.pi and the repo it’s working on” and that’s about it unless it can escape the container.
Sites are slow because with all that excess performance they do more tracking, instead of keeping the website as-is.
Because that's the only thing business managers can come up with in that situation. It's a misaligned goal of users vs businesses.
In my opinion the "user agent" behavior of browsers is long gone, because they're not acting on behalf of their users anymore. They're acting on behalf of businesses.
It's called alignment. And that's the correct word for it in my opinion.
The most important part is that we have to find a way to tackle the knowledge enshittification problem.
Because now that slopcode and slopposts are everywhere, the average quality level will decrease. We had the peak internet knowledge, and it's now gradually getting worse.
That's not a personal opinion, that's how attention matrixes and their keys/values computation works.
As long as there are standards, yes, why not.
In Italian we have a saying: il mondo è bello perché è vario.
The world is beautiful because it’s varied.
the world certainly needs novel ideas. maybe eventually we'll come up with a web framework that doesn't suck - or rather we'll realise that Django had it right all along for all these years.
Since a good LLM can handle any of those 40 web frameworks, I think having 40 web frameworks is becoming less of a problem than it used to be. Actually, implementing ideas in an individual manner will become easier. Remember the Bazaar and the Cathedral? The Bazaar kind of failed on the client side, but LLMs may revive it.
For Work they actively deactivate Linux users for "security reasons", or Microsoft makes their web apps intentionally hostile like disabling copy/paste or disabling photo/picture or file uploads for Linux users when you're allowed in the policies.
Turns out, it's bypassable.
They just check the User Agent and Sec-CH headers, so I built a small browser extension for Chrome that allows to modify those headers.
On top of that I built chromium-profiles [1], my tool for managing those isolated sandboxes so that I can tweak/change them based on the stupid policies per O365 tenant I have to work with.
So I use 3 different profiles for 3 different customers with 3 different security policies set for their organization... For being allowed to use a freaking web app.
That, for me, is the only reason I still have to have chromium installed. Microsoft stupidity.
I wish Firefox would focus on this sort of use case, like the "--pwa" and "--user-data" CLI flags and preinstallable extensions for those profiles. But it can't be done due to how they manage extensions with their own signing cert, how dev mode extensions are always cleared etc. Well, apart from Microsoft intentionally making webapps unusable in Firefox.
https://news.ycombinator.com/item?id=49737132
reply