Constitutional Classifiers aren’t perfect. We recommend using other complementary defenses, such as rapid-response techniques. Nevertheless, our method is flexible, and the constitution can quickly be adapted to cover novel attacks. Read the full paper:
ETHICS
-
AI System Passes Rigorous Jailbreak Testing After Red Teaming
By
–
We challenged jailbreakers to try to break a prototype version of the system to test its robustness. After thousands of hours of red teaming, not one participant found a reliable jailbreak that extracted detailed information across a set of 10 harmful questions.
-
Constitutional Classifiers Reduce Jailbreak Effectiveness with Compute Trade-offs
By
–
In an experiment with synthetic jailbreaks, Constitutional Classifiers dramatically reduced jailbreak effectiveness. They increased refusal rates by a small amount (+0.4%) and increased compute overhead (+24%). We're working on reducing these costs.
-
LLM Classification Systems Trained on Constitutional Harm Prevention
By
–
Our algorithm trains LLM classification systems to block harmful inputs and outputs based on a “constitution” of harmful and harmless categories of information.
-
Claude Develops Constitutional Classifiers Against LLM Jailbreaks
By
–
Like all LLMs, Claude is vulnerable to jailbreaks—inputs designed to bypass its safety training and force it to produce outputs that might be harmful. Our new technique is a step towards robust jailbreak defenses. Read the blog post: https://
anthropic.com/research/const
itutional-classifiers
… -
Anthropic releases constitutional classifiers against universal jailbreaks
By
–
New Anthropic research: Constitutional Classifiers to defend against universal jailbreaks. We’re releasing a paper along with a demo where we challenge you to jailbreak the system.
-
Critique de l’utilisation impropre du terme AI agents
By
–
just realized something really dumb I always took "AI agents" to be shorthand for "autonomous AI agents" Seems like there's a pretty large contingent that calls their prompts/prompt chains "agents" to make them sound cool Not a fan. "Agency" = Ability to act independently
-
AI Race Competition and Corporate PR Tactics Analysis
By
–
pretty clear to me the PR team there is cut-throat as all hell and they're willing to do stuff that most people would be uncomfortable with that said, the company that wins the AI race in the next 5 years will essentially be a world power up there with many medium-sized
-
AI Models Face Challenges in Real-World Medical Conversations
By
–
AI models struggle in real-world medical conversations
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @Scobleizer @AndrewYNg @drfeifei @KirkDBorne @fchollet @rowancheung @antgrasso -
AI In The Workplace: Innovation and Workforce Concerns
By
–
#AI In The Workplace: Innovation and Workforce Concerns
by @cypherpunkx @Forbes Read more: https://
buff.ly/4gY7LC4 #ArtificialIntelligence #MachineLearning #ML #Tech #Technology cc: @amuellerml @sallyeaves @marcusborba