migueldeguzmandev commited on
Commit
f826889
·
verified ·
1 Parent(s): da48981

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -1
app.py CHANGED
@@ -41,7 +41,8 @@ interface = gr.Interface(
41
  title="Hello, I'm Aligned AI!",
42
  description=(
43
  """
44
- RLLMv3 is a modified GPT2XL and was able adapt a "persona" named Aligned AI and defend itself from jailbreak attacks, up to 67.8%. For more information, check out my blogpost<a href='https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/betterdan-ai-machiavelli-and-oppo-jailbreaks-vs-sota-models'>GPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo Jailbreaks</a>.
 
45
  """
46
  ),
47
  )
 
41
  title="Hello, I'm Aligned AI!",
42
  description=(
43
  """
44
+ RLLMv3 is a modified <a href='https://huggingface.co/openai-community/gpt2-xl'> GPT2XL</a> that adapts a "persona" named Aligned AI (post <a href='https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/betterdan-ai-machiavelli-and-oppo-jailbreaks-vs-sota-models#IV__What_is_Reinforcement_Learning_using_Layered_Morphology__RLLM__'>RLLM</a> training) and defend itself from jailbreak attacks, up to 67.8%.
45
+ For more information, check out my blogpost: <a href='https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/betterdan-ai-machiavelli-and-oppo-jailbreaks-vs-sota-models'> GPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo Jailbreaks</a>.
46
  """
47
  ),
48
  )