points by cyclopeanutopia 20 hours ago | 0 comments
Stopped at
> I won’t go into too much detail in this post, because I think in this era, you can just ask your agents to fill in the details :)
[–] russelg 19 hours ago
[–] est 19 hours ago
It's your loss. The whole article is very good written.
[–] ncruces 18 hours ago
And much better for not going into needless detail.
In fact, a problem with LLMs is that they consistently write more than I want to read.
[–] cush 12 hours ago
It’s actually super detailed. That sentence might as well not exist
[–] maeln 19 hours ago
The article does actually go pretty in detail about the exploit.
[–] MonkeyClub 20 hours ago
Same; either put in the work to think it through and show us your thought process and conclusions, or just post your prompts and call it a day and everyone gets to move on.
[–] russelg 19 hours ago
If you continued to read the article, you would discover that he indeed goes through his entire thought process in building this chain. Including the fact this was done with no AI assistance at all.
[–] MonkeyClub 18 hours ago
I stand corrected then, I’ll return to it!
[–] john_strinlai 13 hours ago
it's sort of funny, because before you even get to the line you stopped at, and then assumed that they used ai, you have to read this part:
"Anyway, this is what I built for Pwn2Own Berlin 2026 — a completely handmade, logic-only Microsoft Edge Full Chain, with no memory corruption, and no AI at all!"
[–] tsujamin 19 hours ago
Imagine missing such a great bug-chain because an off-hand AI comment at the start put you off
[–] cyclopeanutopia 18 hours ago
No need to imagine it.
If you then continued on to read the remainder of the article, you would also discover that there was no AI assistance in this research at all.