see this letter and signatories: Open Letter on Transparent AI Cyber Protections
SAFETY
-
New book: A Practical Guide to Reinforcement Learning from Human Feedback
By
–
New release from @PacktDataML at http://
amzn.to/3PMn1ZL "A Practical Guide to Reinforcement Learning from Human Feedback (RLHF)" ๐๐บ๐ฎ๐๐ผ๐ป ๐๐๐บ๐บ๐ฎ๐ฟ๐: RLHF is a powerful approach to AI alignment and human-centered machine learning. By combining reinforcement learning -
Cryptographers Show AI Protections Always Have Holes
By
–
Cryptographers Show That #AI Protections Will Always Have Holes
by Peter Hall @QuantaMagazine Learn more: https://
bit.ly/49VVdto #CyberSecurity #InfoSec #IT #Tech #Technology -
Skeptical questions about frontier AI model availability and plans
By
–
You sure youโll get that frontier level model? You sure the $200 plans will exist? You sure those plans will exist with the same limits? You sure they wonโt be export controlled? โฆ
-
American Restriction on Mythos and Fable 5 for Other Nations
By
–
Claude Mythos & Fable 5 Banned!
The United States has restricted the use of #Mythos and #Fable5 for other nations! https://
youtu.be/rJ1je5IdSTY?si
=l2yfjnio06k6ji-H
โฆ via @YouTube #anthropic #cybersecurity #infosec #AI #databreach @SpirosMargaris @PawlowskiMario @mvollmer1 @gvalan -
AI societal attack risk, Mythos solution, and hidden greater threat
By
–
I was the first to tell you about that risk. But it isn't what really scares me. The AI now can attack our society at scale. Mythos was part of the solution. Companies were using it to close their security vulnerabilities. There's a lot worse than an AI that someday decides
-
Ensemble DL Model for Accurate Tomato Leaf Disease Classification
By
–
Deep Learning Based Ensemble Model for Accurate Tomato Leaf Disease Classification by Leveraging ResNet50! #BigData #Analytics #DataScience #AI #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding
-
Every model can be jailbroken, despite appearing easy
By
–
It's a lot harder than it looks. Every model can be jail broken.
-
No Fable 5 jailbreak against Opus 4.x or GPT 5.x, fortunately
By
–
I'm just glad that no one in the US government thought to try this Fable 5 "jailbreak" against Opus 4.x or GPT 5.x, otherwise I would have absolutely nothing useful to do this weekend.
-
AI for personalized and safer medical care
By
–
AI can support more personalized medical care by helping doctors choose treatments based on each patient's history and needs. Better use of data can lead to safer decisions and more effective care.