Protecting People from Harmful Manipulation
Google DeepMind releases new findings and an evaluation framework to measure AI's potential for harmful manipulation in areas like finance and health, with the goal of enhancing AI safety.
Community feed
evald.ai
A focused stream of recent stories from the sources curated for this community. Latest: Protecting People from Harmful Manipulation, Inside our approach to the Model Spec, and Exclusive: This new benchmark could expose AI’s biggest weakness - Fast Company. Page 4.
Inside our approach to the Model Spec
Learn how OpenAI’s Model Spec serves as a public framework for model behavior, balancing safety, user freedom, and accountability as AI systems advance.
Exclusive: This new benchmark could expose AI’s biggest weakness - Fast Company
Exclusive: This new benchmark could expose AI’s biggest weakness Fast Company
A new GPT-OSS benchmark and DeepSeek R1 updates for latency-optimized reasoning - MLCommons
MLPerf Inference v6.0 introduces GPT-OSS 120B, a new open-weight LLM benchmark, plus a DeepSeek-R1 interactive scenario with support for speculative decoding.
Outlier Emphasizes Expert Contributor Network for AI Model Evaluation - TipRanks
Outlier Emphasizes Expert Contributor Network for AI Model Evaluation TipRanks
Insilico Medicine Highlights AI Benchmark Results in Cardiovascular Drug Target Discovery - TipRanks
Insilico Medicine Highlights AI Benchmark Results in Cardiovascular Drug Target Discovery TipRanks
Impact of modelling assumptions on time horizon results
Alexander Barry examines how different modelling choices affect METR's time horizon estimates.
Standardizing Generative AI Service Evaluation: An API-Centric Benchmarking Approach - MLCommons
MLPerf® Endpoints brings API-native benchmarking, Pareto curve visualizations, and rolling submissions to generative AI infrastructure evaluation.
We spent 2 hours working in the future
Thomas Kwa describes a tabletop exercise where METR researchers simulated having access to ~200-hour time horizon AIs.
Measuring progress toward AGI: A cognitive framework
Google DeepMind proposes a cognitive framework to evaluate AGI and launches a Kaggle hackathon to build capability benchmarks
AI benchmark numbers are meaningless — here’s what to look for instead - MakeUseOf
AI benchmark numbers are meaningless — here’s what to look for instead MakeUseOf
Global Standards, Local Ground Truths: Piloting Multilingual, Multimodal AI Safety Understanding in APAC - MLCommons
MLCommons is developing the AILuminate Culturally-Specific Multimodal Benchmark to close the AI performance and representation gap across APAC cultures, languages, and real-world use cases.
More stories
More stories load automatically as you scroll.