HN user

throwaway314155

1,124 karma
Posts1
Comments891
View on HN

Reverse engineering/decompilation of game binary (Tears of the Kingdom) using Ghidra for modding spanning Java (ghidra), C++ (mods), Python (scripting) and PowerShell (scripting for builds/deploys/etc.).

Fable succeeded in cases where Opus 4.8 consistently marked situations as walled/impossible.

I’ve been using it to use Ghidra to do reverse engineering for modding Zelda: Tears of the Kingdom. Pre-ban it would flag immediately, post-ban it _rarely_ flagged anything and when it did I realized I could just make a memory telling it to convert reverse engineering speech into game development speech, not mentioning pointers, memory, addresses and decompiling. Then the flags mostly went away.

You can sidestep flags by just compacting and then changing the model back at any rate.

flipping between gaming/desktop mode induced a fail state probably 30% of the time until a year ago

That doesn't reflect my experience at all.

You didn’t find this part naive?

But within 20 years, 99% of the workforce in the military, the government, and the private sector will be AIs. This includes the soldiers (by which I mean the robot armies), the superhumanly intelligent advisors and engineers, the police, you name it.

This article is bullshit. You can't get a full model from training on just one artist's work. A pretrained model is required. The pretrained model was likely one which was indeed trained on the works of others without consent.

What's more, their reasoning for abandoning the company was to build out another company with a suspiciously similar idea...

I have bipolar disorder. The more frustrating aspects of coding have historically affected me tenfold (sometimes to the point of severe mania). Using Claude Code has been more like an accessibility tool in that regard. I no longer have to do the frustrating bits. Or at the very least, that aspect of the job is thoroughly diminished. And yes - coding is "fun again".

GPT-5.4 5 months ago

Then they solved this by introducing GPT-5 which was more like a router that put all these models under the hood so you only had to prompt to GPT-5, and it would route to the best suitable model.

Was this ever explicitly confirmed by OpenAI? I've only ever seen it in the form of a rumor.