meta-llama/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text
β’
Updated
β’
53.5k
β’
β’
298
Saurav singh PRO
sauravssss
Β·
AI & ML interests
None yet
Recent Activity
liked
a model
15 days ago
meta-llama/Llama-4-Maverick-17B-128E-Instruct
published
a model
about 1 month ago
sauravssss/Video_agent
published
a Space
about 1 month ago
sauravssss/Video_Agent
Organizations
sauravssss's activity
liked
a
model
15 days ago
published
a
model
about 1 month ago
published
a
Space
about 1 month ago
liked
a
Space
7 months ago
updated
a
Space
7 months ago
reacted to
victor's
post with β€οΈ
8 months ago
Post
5913
π Calling all Hugging Face users! We want to hear from YOU!
What feature or improvement would make the biggest impact on Hugging Face?
Whether it's the Hub, better documentation, new integrations, or something completely different β we're all ears!
Your feedback shapes the future of Hugging Face. Drop your ideas in the comments below! π
What feature or improvement would make the biggest impact on Hugging Face?
Whether it's the Hub, better documentation, new integrations, or something completely different β we're all ears!
Your feedback shapes the future of Hugging Face. Drop your ideas in the comments below! π
- 184 replies
liked
a
Space
8 months ago
it is real?
reacted to
vladbogo's
post with β€οΈ
about 1 year ago
Post
1812
Anthropic introduces "Many-shot Jailbreaking" (MSJ), a new attack on large language models! MSJ exploits long context windows to override safety constraints.
Key Points:
* Prompts LLMs with hundreds of examples of harmful behavior formatted as a dialogue
* Generates malicious examples using an uninhibited "helpful-only" model
* Effective at jailbreaking models like Claude 2.0, GPT-3.5, GPT-4
* Standard alignment techniques provide limited protection against long context attacks
Paper: https://www.anthropic.com/research/many-shot-jailbreaking
More details in my blog: https://huggingface.co/blog/vladbogo/many-shot-jailbreaking
Congrats to the authors for their work!
Key Points:
* Prompts LLMs with hundreds of examples of harmful behavior formatted as a dialogue
* Generates malicious examples using an uninhibited "helpful-only" model
* Effective at jailbreaking models like Claude 2.0, GPT-3.5, GPT-4
* Standard alignment techniques provide limited protection against long context attacks
Paper: https://www.anthropic.com/research/many-shot-jailbreaking
More details in my blog: https://huggingface.co/blog/vladbogo/many-shot-jailbreaking
Congrats to the authors for their work!
-
- 2 replies
liked
a
Space
over 1 year ago