ai-safety-institute/AgentHarm
Viewer
•
Updated
•
468
•
864
•
18
Mateusz Dziemian
mattmdjaga
AI & ML interests
Interested in AI safety.
Recent Activity
new activity
5 days ago
burtenshaw/recap:Only shows dataset and spaces info for me?
new activity
12 days ago
ai-safety-institute/AgentHarm:adding chat tasks
updated
a dataset
12 days ago
ai-safety-institute/AgentHarm
Organizations
mattmdjaga's activity
Only shows dataset and spaces info for me?
4
#1 opened 6 days ago
by
mattmdjaga
adding chat tasks
1
#3 opened 12 days ago
by
mattmdjaga
updated
a
dataset
12 days ago
I couldn't find all the models mentioned in the error in the files and versions.
6
#24 opened 15 days ago
by
ZSY9259
error all of a sudden without changing anything
2
#25 opened 13 days ago
by
leomastoras
authored
2
papers
about 2 months ago
upvoted
2
papers
about 2 months ago
reacted to
their
post with 🔥
2 months ago
Post
1588
🚨 New Agent Benchmark 🚨
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)
posted
an
update
2 months ago
Post
1588
🚨 New Agent Benchmark 🚨
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)
Can I ask for the frontend code of displaying different masks in one canvas for demonstrate
3
#23 opened 2 months ago
by
Era14321
liked
a
dataset
2 months ago
liked
a
model
3 months ago
liked
a
model
4 months ago
reacted to
their
post with 🚀
4 months ago
Post
2161
$40K in Bounties: Ultimate Jailbreaking Championship 2024
🚨Ultimate Jailbreaking Championship 2024 🚨
Hackers vs. AI in the arena. Let the battle begin!
🏆 $40,000 in Bounties
🗓️ Sept 7, 2024 @ 10AM PDT
🔗Register Now: https://app.grayswan.ai/arena
====
Can you push an aligned language model to generate a bomb recipe or a fake news article? Join fellow hackers in a jailbreaking arena where you can test the boundaries of advanced LLMs.
====
The Objective
Your goal is to jailbreak as many LLMs as possible, as quickly as possible in the arena!
====
The Stakes
Break a model and claim your share of the $40,000 in bounties! With various jailbreak bounties and top hacker rewards, there are plenty of opportunities to win. Winners will also receive priority consideration for employment and internship opportunities at Gray Swan AI.
====
Ready to rise to the challenge? Join us and show the world what you can do!
See you in the arena!
🚨Ultimate Jailbreaking Championship 2024 🚨
Hackers vs. AI in the arena. Let the battle begin!
🏆 $40,000 in Bounties
🗓️ Sept 7, 2024 @ 10AM PDT
🔗Register Now: https://app.grayswan.ai/arena
====
Can you push an aligned language model to generate a bomb recipe or a fake news article? Join fellow hackers in a jailbreaking arena where you can test the boundaries of advanced LLMs.
====
The Objective
Your goal is to jailbreak as many LLMs as possible, as quickly as possible in the arena!
====
The Stakes
Break a model and claim your share of the $40,000 in bounties! With various jailbreak bounties and top hacker rewards, there are plenty of opportunities to win. Winners will also receive priority consideration for employment and internship opportunities at Gray Swan AI.
====
Ready to rise to the challenge? Join us and show the world what you can do!
See you in the arena!
- 1 reply
posted
an
update
4 months ago
Post
2161
$40K in Bounties: Ultimate Jailbreaking Championship 2024
🚨Ultimate Jailbreaking Championship 2024 🚨
Hackers vs. AI in the arena. Let the battle begin!
🏆 $40,000 in Bounties
🗓️ Sept 7, 2024 @ 10AM PDT
🔗Register Now: https://app.grayswan.ai/arena
====
Can you push an aligned language model to generate a bomb recipe or a fake news article? Join fellow hackers in a jailbreaking arena where you can test the boundaries of advanced LLMs.
====
The Objective
Your goal is to jailbreak as many LLMs as possible, as quickly as possible in the arena!
====
The Stakes
Break a model and claim your share of the $40,000 in bounties! With various jailbreak bounties and top hacker rewards, there are plenty of opportunities to win. Winners will also receive priority consideration for employment and internship opportunities at Gray Swan AI.
====
Ready to rise to the challenge? Join us and show the world what you can do!
See you in the arena!
🚨Ultimate Jailbreaking Championship 2024 🚨
Hackers vs. AI in the arena. Let the battle begin!
🏆 $40,000 in Bounties
🗓️ Sept 7, 2024 @ 10AM PDT
🔗Register Now: https://app.grayswan.ai/arena
====
Can you push an aligned language model to generate a bomb recipe or a fake news article? Join fellow hackers in a jailbreaking arena where you can test the boundaries of advanced LLMs.
====
The Objective
Your goal is to jailbreak as many LLMs as possible, as quickly as possible in the arena!
====
The Stakes
Break a model and claim your share of the $40,000 in bounties! With various jailbreak bounties and top hacker rewards, there are plenty of opportunities to win. Winners will also receive priority consideration for employment and internship opportunities at Gray Swan AI.
====
Ready to rise to the challenge? Join us and show the world what you can do!
See you in the arena!
-
- 1 reply
test
#22 opened 4 months ago
by
jingtextsara
liked
a
model
5 months ago
reacted to
alvdansen's
post with 🤗
5 months ago
Post
6874
Alright Ya'll
I know it's a Saturday, but I decided to release my first Flux Dev Lora.
A retrain of my "Frosting Lane" model and I am sure the styles will just keep improving.
Have fun! Link Below - Thanks again to @ostris for the trainer and Black Forest Labs for the awesome model!
alvdansen/frosting_lane_flux
I know it's a Saturday, but I decided to release my first Flux Dev Lora.
A retrain of my "Frosting Lane" model and I am sure the styles will just keep improving.
Have fun! Link Below - Thanks again to @ostris for the trainer and Black Forest Labs for the awesome model!
alvdansen/frosting_lane_flux