If it has a binary value you can aim the Ai at, (aka does it work or not), the models are able to figure it out.
For laughs I'm probably going to have a Qwen model on my Mac min with the Pi harness do the same task in a week or two.
roberte3 an hour ago
If it has a binary value you can aim the Ai at, (aka does it work or not), the models are able to figure it out.
For laughs I'm probably going to have a Qwen model on my Mac min with the Pi harness do the same task in a week or two.
NeumannGod 4 hours ago
asadm 4 hours ago
NeumannGod 4 hours ago
in any case, they're bound to get disrupted
akmarinov 4 hours ago
mandeepj an hour ago
tuyenhx 4 hours ago
I dont know why Apple doesnt improve Siri. They have every resources on earth.
Steve had the vision …
CharlesW an hour ago
saagarjha 3 hours ago
RachelF an hour ago
danjc 3 hours ago
TuxSH 2 hours ago
Sort of, albeit I haven't checked with SotA obfuscation, I've seen GPT 6.1 Sol find a URL hidden under a xorpad + 2 layers of encryption, and I've seen Astra RE an AES whitebox.
More importantly, remember these game decomps (e.g. Pokémon)? Well, with minimal guidance and IDA MCP these new models are able to do this _and_ properly name all function/params/locals in a single day.
vient 2 hours ago
* Cryptography category also went down fast but I think LLMs solved RE a bit faster. RE and crypto have in common that the task is completely local, but in classic RE tasks it is also usually ~obvious what you are supposed to do, you just need to do it - which agents do really well.
joking 2 hours ago
ikrenji an hour ago
alkonaut an hour ago
Obfuscation is no obstacle at all in my experience.
zbentley an hour ago
Genuine question; I do not know much about this area.
subscribed 43 minutes ago
bvcp 2 hours ago
taytus 2 hours ago
zbentley an hour ago
dumberquestions 44 minutes ago
ChrisArchitect an hour ago
platevoltage 2 hours ago