Our algorithm trains LLM classification systems to block harmful inputs and outputs based on a “constitution” of harmful and harmless categories of information.
ETHICS
-
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 -
AI Reaching Single-Digit Economic Task Capability Milestone
By
–
“my very approximate vibe is that it can do a single-digit percentage of all economically valuable tasks in the world, which is a wild milestone.” I really wish OpenAI and other frontier AI labs were doing to plan for the impact of these tools on people and jobs.
-
Society Running on AI Systems No One Understands: Vibe Coding
By
–
YOLO How long before the entirety of human society runs on systems built via vibe coding. No one knows how it works. It's just chatbots all the way down PS: I'm currently like a 3 on the 1 to 10 slider from non-vibe to vibe coding. Need to try 10 or 11.
-
5-Hour AI Future Conversation with Dylan522p and Nato Lambert
By
–
Here's the links for my 5-hour conversation on the future of AI with @dylan522p and @natolambert
: YouTube: https://
youtube.com/watch?v=_1f-o0
nqpEI
… Spotify: https://
open.spotify.com/show/2MAi0BvDc
6GTFvKFPXnkCL
… Podcast: https://
lexfridman.com/podcast