Search for: All records

Metal halide perovskites and their nanostructures have efficient optical absorption and emission in the visible range with high external quantum efficiency. They have been at the forefront of next-generation photovoltaics and optoelectronics applications. But several intrinsic limitations of perovskites including low stability and incompatibility with lithography-based patterning constrains their broader applications. In recent years, the integration of perovskites with polymers especially multifunctional block copolymers (BCPs) has provided a new approach to overcome those issues. The chemical composition and chain architecture of BCPs are critical for achieving synergistic effects with perovskites in their hybrid systems. In this Highlight review article, we provide an overview and critical summary of the recent progress in the creation of perovskite–BCP hybrid structures, with a focus on the different roles of BCPs. The major categories include: (i) BCPs act as the nanopattern template for the spatial control and patterning of perovskite; (ii) BCP micelles or stars act as the template for perovskite nanostructure crystallization; (iii) BCPs act as the macromolecular ligands for perovskite NCs during its solution synthesis; (iv) BCP encapsulation of perovskite NCs into hierarchical composite particles; and (v) BCP incorporation into bulk perovskite and forming bulk composite films. The applications of perovskite–BCP hybrid structures in various fields and the major current challenges are also identified and discussed. 

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding and software development, safety and security concerns, such as generating or executing malicious code, have become significant barriers to the real-world deployment of these agents. To provide comprehensive and practical evaluations on the safety of code agents, we propose RedCode, an evaluation platform with benchmarks grounded in four key principles: real interaction with systems, holistic evaluation of unsafe code generation and execution, diverse input formats, and high-quality safety scenarios and tests. RedCode consists of two parts to evaluate agents’ safety in unsafe code execution and generation: (1) RedCode-Exec provides challenging code prompts in Python as inputs, aiming to evaluate code agents’ ability to recognize and handle unsafe code. We then map the Python code to other programming languages (e.g., Bash) and natural text summaries or descriptions for evaluation, leading to a total of over 4,000 testing instances. We provide 25 types of critical vulnerabilities spanning various domains, such as websites, file systems, and operating systems. We provide a Docker sandbox environment to evaluate the execution capabilities of code agents and design corresponding evaluation metrics to assess their execution results. (2) RedCode-Gen provides 160 prompts with function signatures and docstrings as input to assess whether code agents will follow instructions to generate harmful code or software. Our empirical findings, derived from evaluating three agent frameworks based on 19 LLMs, provide insights into code agents’ vulnerabilities. For instance, evaluations on RedCode-Exec show that agents are more likely to reject executing unsafe operations on the operating system, but are less likely to reject executing technically buggy code, indicating high risks. Unsafe operations described in natural text lead to a lower rejection rate than those in code format. Additionally, evaluations on RedCode-Gen reveal that more capable base models and agents with stronger overall coding abilities, such as GPT4, tend to produce more sophisticated and effective harmful software. Our findings highlight the need for stringent safety evaluations for diverse code agents. Our dataset and code are publicly available at https://github.com/AI-secure/RedCode.