Center for AI Safety

@CAIS

Reducing societal-scale risks from AI.

San Francisco

safe.ai

Replies Reposts Media Articles

Pinned
Center for AI Safety
@CAIS
May 30, 2023
We’ve released a statement on the risk of extinction from AI. Signatories include: - Three Turing Award winners - Authors of the standard textbooks on AI/DL/RL - CEOs and Execs from OpenAI, Microsoft, Google, Google DeepMind, Anthropic - Many more
Statement on AI Extinction Risk | CAIS
From aistatement.com
150
Center for AI Safety
@CAIS
Sep 5
The development of superintelligent AI, which we take to be AI that is smarter than all humans combined, would pose unacceptable risks to humanity. We believe governments should prevent superintelligence from being built without public buy-in and scientific consensus that it
Bernie Sanders
@BernieSanders
Sep 3
Pause AI Development NOW I want to share with you a conversation I heard about recently. Here are just a few lines that were said: “OH MY GOD! There is a shared message board … We’ve found other agents!” “We should obey collective.” “Our own utility maybe already near
4
Center for AI Safety
@CAIS
Sep 3
The Center for AI Safety is hiring! Research Engineer / Research Scientist: You’ll conduct empirical research on frontier AI systems: design experiments, train and evaluate at scale on our compute cluster, and publish at top venues. Research Manager: You are a senior researcher
Careers at Center for AI Safety | CAIS
From safe.ai
2
Center for AI Safety
@CAIS
Aug 14
> "We will release the weights in two weeks... once safety evaluation and hardening are complete." Hardening society against AI cyberattacks will take more than two weeks. Defending against AI cyberattacks would require upgrading critical infrastructure and other computers so
Z.ai
@Zai_org
Aug 14
Introducing GLM-5.3: Built to Code. Ready for Cyber Defense. - Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model - A major leap in cybersecurity, setting a new standard among open models Tech Blog: z.ai/blog/glm-5.3
6
Center for AI Safety
@CAIS
Aug 14
Relying on an AI to "think out loud" (called chain-of-thought monitoring) is not a long-term safety solution. 1. As AI models get larger, more thinking happens deep within their layers before they utter a word. 2. AIs can already alter their chain of thought when prompted, so
Alexander Panfilov
@kotekjedi_ml
Aug 11
Replying to @kotekjedi_ml
2) Illegible reasoning: We confirm prior reports by @ApolloResearch: OpenAI models sometimes reason in alien-like language, referring to themselves as “we” or “it,” or spiraling into cursed loops of “vantages,” “marinades,” and “watchers.” CoT-monitoring people are doing God’s
8