Unanticipated runtime errors, lacking predefined handlers, can abruptly terminate execution and lead to severe consequences, such as data loss or system crashes. Despite extensive efforts to identify potential errors during the development phase, such unanticipated errors remain a challenge to to be entirely eliminated, making the runtime mitigation measurements still indispensable to minimize their impact. Automated self-healing techniques, such as reusing existing handlers, have been investigated to reduce the loss coming through with the execution termination. However, the usability of existing methods is retained by their predefined heuristic rules and they fail to handle diverse runtime errors adaptively. Recently, the advent of Large Language Models (LLMs) has opened new avenues for addressing this problem. Inspired by their remarkable capabilities in understanding and generating code, we propose to deal with the runtime errors in a real-time manner using LLMs. Specifically, we propose Healer, the first LLM-assisted self-healing framework for handling runtime errors. When an unhandled runtime error occurs, Healer will be activated to generate a piece of error-handling code with the help of its internal LLM and the code will be executed inside the runtime environment owned by the framework to obtain a rectified program state from which the program should continue its execution. Our exploratory study evaluates the performance of Healer using four different code benchmarks and three state-of-the-art LLMs, GPT-3.5, GPT-4, and CodeQwen-7B. Results show that, without the need for any fine-tuning, GPT-4 can successfully help programs recover from 72.8% of runtime errors, highlighting the potential of LLMs in handling runtime errors.

"Games are very rapidly solved these days," says Ion Hazzikostas, the game director of World of Warcraft. Hazzikostas, known to the World of Warcraft community as Watcher, has developed the 16-year-old massively multiplayer online role-playing game since 2008. On a call with WIRED, he reminisced about how, early in the history of games, before raid walk-through videos, data-mining dumps, and Easter egg maps, opacity was a double-edged sword. To explain, he swerved over to Street Fighter. "You'd have a whole competitive hierarchy in a local arcade, a local video game store, where there was some character that was perceived as the best or the strongest because some person in the neighborhood was great with them," he says.

The potential of Artificial Intelligence (AI) to tackle challenging problems that afflict society is enormous, particularly in the areas of healthcare, conservation and public safety and security. Many problems in these domains involve harnessing social networks of under-served communities to enable positive change, e.g., using social networks of homeless youth to raise awareness about Human Immunodeficiency Virus (HIV) and other STDs. Unfortunately, most of these real-world problems are characterized by uncertainties about social network structure and influence models, and previous research in AI fails to sufficiently address these uncertainties. This thesis addresses these shortcomings by advancing the state-of-the-art to a new generation of algorithms for interventions in social networks. In particular, this thesis describes the design and development of new influence maximization algorithms which can handle various uncertainties that commonly exist in real-world social networks. These algorithms utilize techniques from sequential planning problems and social network theory to develop new kinds of AI algorithms. Further, this thesis also demonstrates the real-world impact of these algorithms by describing their deployment in three pilot studies to spread awareness about HIV among actual homeless youth in Los Angeles. This represents one of the first-ever deployments of computer science based influence maximization algorithms in this domain. Our results show that our AI algorithms improved upon the state-of-the-art by 160% in the real-world. We discuss research and implementation challenges faced in deploying these algorithms, and lessons that can be gleaned for future deployment of such algorithms. The positive results from these deployments illustrate the enormous potential of AI in addressing societally relevant problems.

If people know you're a girl, you begin to attract unsolicited attention from your male gaming counterparts. Just like everywhere else in the world, there are a lot of lonely people (of all genders) out there playing MMORPGs, but it's still predominantly male. So if everyone knows you're a "real" girl (yes, it's actually pretty common for guys to play female characters), it's sort of like wolves circling a straggling sheep. Even in my raiding guild, which is a pretty friendly group, there is a fairly constant stream of flirtation and innuendo even though everyone I'm playing with knows I'm married and have a bunch of kids. So you learn to develop boundaries.