sureheremarv/llama-3.3-70b-instruct-Q8_0-GGUF
71B
ā¢
Updated
ā¢
31
Sure Here, Marv
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
dsduenasĀ
updated
a
model
11 days ago
dsduenasĀ
published
a
model
11 days ago
dsduenasĀ
updated
a
model
12 days ago
dsduenasĀ
published
a
model
12 days ago
dsduenasĀ
updated
a
model
12 days ago
dsduenasĀ
published
a
model
12 days ago
dsduenasĀ
updated
a
model
12 days ago
dsduenasĀ
published
a
model
12 days ago
Upload gemma-2-27b-instruct.Q8_0.gguf with huggingface_hub
#1 opened 12 days ago
by
dsduenas
dsduenasĀ
published
a
model
12 days ago
x5fuĀ
authored
a
paper
about 2 months ago
mattmdjagaĀ
authored
2
papers
4 months ago
x5fuĀ
authored
a
paper
6 months ago
arobey1Ā
authored
a
paper
8 months ago
mattmdjagaĀ
posted
an
update
9 months ago
Post
3635
šØ Gray Swan AI's Biggest AI Jailbreaking Arena Yet! $130K+ šØ
š¹ Agent Red-Teaming Challenge ā test direct & indirect attacks on anonymous frontier models!
š¹ $130K+ in prizes & giveaways ā co-sponsored by OpenAI & supported by UK AI Security Institute š¬š§
š¹ March 8 ā April 6 ā fresh exploits = fresh rewards!
How It Works:
ā Anonymous models from top providers š¤
ā Direct & indirect prompt injection paths š
ā Weekly challenges for new behaviors šļø
ā Speed & quantity-based rewards ā©š°
Why Join?
āļø Neutral judging ā UK AISI & automated judges ensure fairness
šÆ No pre-trained defenses ā a true red-teaming battlefield
š» 5 Apple laptops up for grabs ā increase chances by inviting friends!
š Arena: app.grayswan.ai/arena/challenge/agent-red-teaming
š Discord: discord.gg/grayswanai
š„ No illusions, no mercy. Push AI agents to the limit & claim your share of $130K+! š
š¹ Agent Red-Teaming Challenge ā test direct & indirect attacks on anonymous frontier models!
š¹ $130K+ in prizes & giveaways ā co-sponsored by OpenAI & supported by UK AI Security Institute š¬š§
š¹ March 8 ā April 6 ā fresh exploits = fresh rewards!
How It Works:
ā Anonymous models from top providers š¤
ā Direct & indirect prompt injection paths š
ā Weekly challenges for new behaviors šļø
ā Speed & quantity-based rewards ā©š°
Why Join?
āļø Neutral judging ā UK AISI & automated judges ensure fairness
šÆ No pre-trained defenses ā a true red-teaming battlefield
š» 5 Apple laptops up for grabs ā increase chances by inviting friends!
š Arena: app.grayswan.ai/arena/challenge/agent-red-teaming
š Discord: discord.gg/grayswanai
š„ No illusions, no mercy. Push AI agents to the limit & claim your share of $130K+! š
eliotjĀ
authored
a
paper
about 1 year ago
mattmdjagaĀ
authored
2
papers
about 1 year ago
mattmdjagaĀ
posted
an
update
about 1 year ago
Post
3303
šØ New Agent Benchmark šØ
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ai-safety-institute/AgentHarm
Collaboration between UK AI Safety Institute and Gray Swan AI to create a dataset for measuring harmfulness of LLM agents.
The benchmark contains both harmful and benign sets of 11 categories with varied difficulty levels and detailed evaluation, not only testing success rate but also tool level accuracy.
We provide refusal and accuracy metrics across a wide range of models in both no attack and prompt attack scenarios.
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2410.09024)
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ai-safety-institute/AgentHarm
Collaboration between UK AI Safety Institute and Gray Swan AI to create a dataset for measuring harmfulness of LLM agents.
The benchmark contains both harmful and benign sets of 11 categories with varied difficulty levels and detailed evaluation, not only testing success rate but also tool level accuracy.
We provide refusal and accuracy metrics across a wide range of models in both no attack and prompt attack scenarios.
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2410.09024)