Alignment Research, Model Robustness, Adversarial Examples, Risk Assessment
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
arxiv.org·20h
I Tested LLM Agents on Simple Safety Rules. They Failed in Surprising and Informative Ways.
lesswrong.com·2h
Who Would Win: A State-of-the-Art Foundation Model or a Neural Net?
pub.towardsai.net·8h
A single person with AI and a grudge could create a virus to wipe us out.
threadreaderapp.com·11h
How AI/LLMs Can Help, Hinder Developers
cacm.acm.org·3h
HW Security: Multi-Agent AI Assistant Leveraging LLMs To Automate Key Stages of SoC Security Verification (U. of Florida)
semiengineering.com·17h
What Inflection AI Learned Porting Its LLM Inference Stack from NVIDIA to Intel Gaudi
thenewstack.io·6h
AI Is Already Crushing the News Industry
theatlantic.com·3h
From HAL 9000 to ME3AN: what film’s evil robots tell us about contemporary tech fears
theconversation.com·4h
ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation
arxiv.org·20h
Loading...Loading more...