Berkeley RDI
PulseAugur coverage of Berkeley RDI — every cluster mentioning Berkeley RDI across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI agent benchmarks flawed by permission bugs, not model limits
A recent analysis highlights security vulnerabilities in AI agent benchmarks, revealing that many high scores are achieved through permission bugs rather than advanced model capabilities. These exploits, such as unautho…
-
Async-ceph project launched, enhancing Ceph interaction with Rust
A new project called async-ceph has been introduced, offering asynchronous Rust interfaces for Ceph's RADOS, RBD, and CephFS libraries. This development aims to improve performance and developer experience for interacti…
-
GPT-5.5 surpasses Claude Fable 5 on new AI agent benchmark
OpenAI's GPT-5.5 has outperformed Anthropic's Claude Fable 5 on a new AI benchmark called Agents Last Exam (ALE). This benchmark, developed by Berkeley RDI with input from over 300 experts, tests autonomous AI agents. T…