News for hackers. Stuff that matters.
Re:Email Obfuscation Rendered Almost Ineffective Against Cha... by woadwarrior01 on Sunday November 05, 2023 @10:25AM (#38151895)
It's even easier than that. There's no need to even fine tune an LLMs to do it. Here's a screenshot[1] of a 4 bit quantised version of an off the shelf open LLM (WizardLM 13B v1.2) doing it on my Mac.

[1]: https://imgur.com/a/S9jnHWJ

Re:Email Obfuscation Rendered Almost Ineffective Against Cha... by a_wild_dandan on Sunday November 05, 2023 @11:22AM (#38152516)
Yep, I use Llama2 70b for larger tasks on my MacBook and 13b for more “single use” type tasks. It’s a game changer.
Re:Email Obfuscation Rendered Almost Ineffective Against Cha... by Tostino on Sunday November 05, 2023 @09:15PM (#38158013)
That may be true, and for some tasks the accuracy may be high enough. I have gotten much more consistency in my tasks by fine tuning though.

Getting a consistently good result for one shape of input may not indicate that same performance for another shape of input for example.

Re:Email Obfuscation Rendered Almost Ineffective Against Cha... by manwithaplan on Monday November 06, 2023 @11:25AM (#38164670)
The system confabulated the www subdomain of the “URL provided in the text”, right?