Appending "Good." before clarifying questions actually helps with that suprisingly well.

You're absolutely right! No, really: I've never had this problem of unprompted changes when I'm just asking, but I always (I think even in real-life conversations with real people) start with feedback: "Works great. What happens if..."

I think people having different styles of prompting LLMs leads to different model preferences. It's like you can work better with some colleagues while with others it does not really "click".

Plus one to this -- also "very well" can indicate that I'm satisfied with the output produced and now we are on to the next stage.

GPT models are generally much better at C++, although they sometimes tend to produce correct but overengineered code, and the operator has to keep an eye on that.

Now this is bad. "Registered App Stores" seems like a way to satisfy regulators before taking away the user's right to execute arbitrary code on their devices (or as it's called in modern corporate newspeak: sideloading).

I haven't looked at the MCP server, but generally, reverse engineering with AI is quite underrated. I’ve had success extracting encryption keys from an android app that uses encryption to vendor-lock users by forcing them to use that specific app to open files that should otherwise be in an open format.

By the way, this app had embedded the key into the shader, and it was required to actually run this shader on android device to obtain the key.

My friend and I were able to give claude a (no longer updated) unity arcade game. It decompiled it and created a one-to-one typescript port so it can run in the browser and now we're adding multiplayer support (for personal use, don't worry HN - we won't be distributing it). I'm very excited for what AI can do for legacy software.

> By the way, this app had embedded the key into the shader, and it was required to actually run this shader on android device to obtain the key.

Oh that's clever. I don't suppose you can share more about how this was done?

I agree, I tried RE using multiple tools connected to MCP and a agent, it was tasked to recreate what the source code might have looked like from a binary and what possible vulnerabilities there could be. It did a incredible job when I compared it to the actual source.

You should probably look into https://justthebrowser.com/. This software sets up browser corporate policies to achieve exactly what you want.

By getting you run run arbitrary code when in the end all is does is install this policy file: https://raw.githubusercontent.com/corbindavenport/just-the-b...

Maybe we need a justtheconfig.com

Social media age restriation is just an anonymity ban in disguise. Governments should focus on regulations knowingly addictive and overly engaging mechanics instead.

I really hope this would be geared towards clients being able to verify the server state or just general server related usecases, instead of trying to replicate SafetyNet-style corporate dystopia on the desktop.

Yes, but such tools aren't popular enough for the censor to specifically target.

If it's mandated that banking apps must not run in a user-controlled environment for the sake of security, users should have the right to refuse such "protection" by signing a piece of paperwork at the banks office.

So, how airgapped systems are supposed to get activated from now on?

You pay a lot of money for a special contract, or you plug it into the internet. Whether from incompetence or malice, Microsoft would strongly prefer you did the latter.