If you’re interested in working with us on this and related problems, our Alignment Science team is hiring. Take a look at our Research Engineer job listing: https://
jobs.lever.co/Anthropic/444e
7d1e-ec6a-4d18-b712-0cb79c27f00f
…
ETHICS
-
Anthropic Alignment Science Team Hiring Research Engineer
By
–
-
Anthropic Research: Many-Shot Jailbreaking Techniques Analysis
By
–
Research: https://
anthropic.com/research/many-
shot-jailbreaking
… -
Repetition Jailbreak: Context Window Vulnerability in Large Language Models
By
–
New jailbreaking technique: pure repetition. AIs are getting big context windows, it turns out if you fill a lot of it with examples of bad behavior, the AI becomes much more willing to breach its own guardrails. Security people are used to rules-based systems. This is weirder.
-
Profit-Driven Actors Exploiting Commons: Economic and Ethical Concerns
By
–
Ah, yes. So the pillaging of the commons by profit-motivated actors. That was certainly another pathology here, in addition to people having no home training.
-
FOSS Culture Toxic Behavior Creates Security Vulnerabilities
By
–
One striking thing about the xz backdoor is how the uncool, mean standards of behavior common in FOSS, that many of us decried for years, & that many defended as authentic, tough, etc., ended up being not just exclusionary loser behavior, but a significant attack surface.
-
LLMs Risk: Hallucinations and False Source Attribution
By
–
I think that's OK: it's an analogy. Bears could kill you. LLMs could embarrass you by causing you to cite a non-existent source.
-
LLM Hallucinations in Medical Assessments: A Critical Concern
By
–
In a recent study, 4 out of 5 LLMs hallucinated a significant proportion of sources for their answers to medical questions. Should we be using them for medical assessments?
-
Employees Using AI Secretly: The Hidden Opportunity
By
–
The biggest AI opportunity companies are missing is that their employees are rapidly adopting AI & figuring out how to use it for work… and not telling leadership Organizations that have unclear AI policies are not stopping people from using AI, they stop them from sharing uses
-
Three Laws of Robotics and 50 Million Robots Sold
By
–
My three laws of robotics. The companies that I have founded have sold 50+ million real robots to real customers; research robots, home cleaning, nuclear power plant inspection, military ground robots, upper body humanoids in factories, and now at http://
Robust.AI, -
Smart Glass Technology Ensures Privacy Through Artificial Intelligence
By
–
This Smart Glass will ensure your #Privacy
— Ronald van Loon (@Ronald_vanLoon) 2 avril 2024
via @FrRonconi#AI #ArtificialIntelligence #EmergingTech #Technology #FutureOfWork
cc: @karpathy @ravikikan @patrickgunz_ch pic.twitter.com/9R0UW2pQXIThis Smart Glass will ensure your #Privacy
via @FrRonconi #AI #ArtificialIntelligence #EmergingTech #Technology #FutureOfWork cc: @karpathy @ravikikan @patrickgunz_ch