The full version of OpenAI’s o1 reasoning model has been out for a week. Thoughts so far?
RESEARCH
-
Command R7B Delivers Industry-Leading Performance Across Math, Code
By
–
Command R7B offers industry-leading performance in its class on math and reasoning, code, and multilingual tasks while using fewer parameters.
-
Command R7B Outperforms Competing Open-Weights Models
By
–
Command R7B is available today on our platform and @HuggingFace
. Notably, It outperforms similarly sized open-weights models on their leaderboard across all tasks. -
AI Content Detectors: Testing Accuracy and Effectiveness
By
–
I tested 9 AI content detectors – and these 2 correctly identified AI text every time https://
zd.net/3Vq0fa7
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Open-Sourcing Jailbreaking Defense Benchmarking Tool
By
–
We’re open-sourcing our code so others can build on our work. We hope it assists in benchmarking misuse risk, and designing defenses to safeguard against strong adaptive attacks. Paper: https://
arxiv.org/abs/2412.03556
GitHub: https://
github.com/jplhughes/bon-
jailbreaking
…
Website: https://
jplhughes.github.io/bon-jailbreaki
ng
… -
Anthropic Fellows Program: Collaboration and Full-Time Opportunities
By
–
This work was a collaboration between Anthropic, @ucl
, and @MATSProgram
. If you’re interested in collaborating with us, please apply to our new Anthropic Fellows program: https://
alignment.anthropic.com/2024/anthropic
-fellows-program/
… For full-time roles at Anthropic, apply here: -
Best-of-N Jailbreak Technique Achieves Faster ASR on Claude Models
By
–
Best-of-N can be composed with other jailbreak techniques for even more effective attacks with improved sample efficiency. Combined with many-shot jailbreaking on text inputs, Best-of-N achieves the same ASR 28x faster for Claude 3.5 Sonnet and 70x faster for Claude 3 Opus.
-
Frontier AI Labs Responsible Vulnerability Disclosure via Forum
By
–
Before sharing these results publicly, we disclosed the vulnerability to other frontier AI labs via the Frontier Model Forum (
@fmf_org
). Responsible disclosure of jailbreaks is essential, especially as AI models become more capable. -
Jailbreak Attack Success Rates Scale with Compute Power
By
–
Attack success rates scale predictably with sample size, following a power law. More samples lead to higher success rates; Best-of-N can harness more compute for tougher jailbreaks. This predictable scaling allows accurate forecasting of ASR when using more samples.
-
Best-of-N Jailbreaking Techniques for Vision Language Models
By
–
Best-of-N isn't limited to text. We jailbroke vision language models by repeatedly generating images with different backgrounds and overlaid text in different fonts. For audio, we adjusted pitch, speed, and background noise. Some examples are here: https://
jplhughes.github.io/bon-jailbreaki
ng/#examples
…