Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost performance in these settings. However, despite its increasing popularity, existing studies of self-repair have been limited in scope; in many settings, its efficacy thus remains poorly understood. In this paper, we analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS. We find that when the cost of carrying out repair is taken into account, performance gains are often modest, vary a lot between subsets of the data, and are sometimes not present at all. We hypothesize that this is because self-repair is bottlenecked by the model's ability to provide feedback on its own code; using a stronger model to artificially boost the quality of the feedback, we observe substantially larger performance gains. Similarly, a small-scale study in which we provide GPT-4 with feedback from human participants suggests that even for the strongest models, self-repair still lags far behind what can be achieved with human-level debugging.

The rapid advancement and adoption of generative AI (GenAI) technologies like ChatGPT signify the dawn of "The Age of AI." (Gates, 2023; Kissinger, Schmidt, & Huttenlocher, 2021) These developments mark a significant leap in the capabilities and adoption of AI systems. However, for many people, the swift and disorienting integration of AI into daily life raises many issues (Cugurullo & Acheampong, 2023; Fietta, Zecchinato, Stasi, Polato, & Monaro, 2022; Qasem, 2023). Concerns include the potential impacts on employment, privacy, and inequality, along with broader societal implications like human rights, mental health, and the preservation of democratic norms (Future of Life Institute, 2023; Prabhakaran, Mitchell, Gebru, & Gabriel, 2022; Shahriari & Shahriari, 2017; Stray, 2020). This article argues for the importance of wellbeing as a key objective in AI and for human-centered design (HCD) as a key methodology. Based on this framing, it shares a set of key challenges that will face designers of AI for wellbeing, or Positive AI. The idea that AI should support wellbeing is not uncommon. In 2018, Zuckerberg (2018) (CEO of Meta, previously Facebook) publicly stated that wellbeing should be the goal of AI. Further, in an interview Jan Leike (Wiblin, n.d.) (head of the'Superalignment' research lab at OpenAI) said AI optimization should align to "flourishing."

Lawmakers and scientists have warned ChatGPT could help anyone develop deadly bioweapons that would wreck havoc on the world. While studies have suggested it is possible, new research from the chatbot's creator OpenAI claims GPT-4 - the lasted version -provides at most a mild uplift in biological threat creation accuracy. OpenAI conducted a study of 100 human participants who were separated into groups - one used the AI to craft a biotattack and the other just the internet. The study found that'GPT-4 may increase experts' ability to access information about biological threats, particularly for accuracy and completeness of tasks,' according to OpenAI's report. Results showed that the LLM group was able to obtain more information about bioweapons than the internet only group for ideation and acquisition, but more information is needed to accurately identify any potential risks.

Running a local AI large language model (LLM) or chatbot on your PC allows you to ask whatever questions you want in utter privacy. But these LLMs are often difficult to set up and configure. There's a solution: an application called GPT4All. For now, GPT4All represents the best combination of ease of use and flexibility. It's not nearly as accommodating as some of the more complex frameworks and applications, but you can have it up and running in mere minutes with just a few clicks.

Interacting with a contemporary LLM-based conversational agent can create an illusion of being in the presence of a thinking creature. Yet, in their very nature, such systems are fundamentally not like us.

Challenges and opportunities faced by computing educators and students adapting to LLMs capable of generating accurate source code from natural-language problem descriptions.

As owner of GitHub and lead investor in OpenAI, the developer of the GPT-x series of large language models (LLMs), it did not take long for Microsoft to see the potential for collaboration between the two. Three years ago, GitHub partnered with OpenAI to develop Codex as an automated assistant for programmers, quickly followed by the Copilot code-completion tool. The public release of ChatGPT by OpenAI toward the end of 2022 made the technology even more widely available to software developers and people learning to program, with other vendors joining in the effort to automate the job of writing software using LLMs. Rapid scaling has enabled major improvements in the ability of artificial intelligence (AI) to turn natural-language requests into working code. Workplace studies have claimed LLMs boost productivity on real-world projects.

More than half of undergraduates say they consult artificial intelligence programmes to help with their essays, while schools are trialling its use in the classroom. A survey of more than 1,000 UK undergraduates, conducted by the Higher Education Policy Institute (Hepi), found 53% were using AI to generate material for work they would be marked on. One in four are using applications such as Google Bard or ChatGPT to suggest topics and one in eight are using them to create content. Just 5% admitted to copying and pasting unedited AI-generated text into their assessments. Teachers are also seeking to use AI to streamline their work, with the Education Endowment Foundation (EEF) signing up secondary schools for a new research project into the use of AI to generate lesson plans and teaching materials as well as exams and model answers.

State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed datasets to teach conversational agents the appropriate social paradigms to respond effectively to specifically designed hazardous content. However, models trained on these adversarial datasets still struggle to recognize subtle unsafe situations that appear naturally in conversations or introduce an inappropriate response in a casual context. To understand the extent of this problem, we study prosociality in both adversarial and casual dialog contexts and audit the response quality of general-purpose language models in terms of propensity to produce unsafe content. We propose a dual-step fine-tuning process to address these issues using a socially aware n-pair contrastive loss. Subsequently, we train a base model that integrates prosocial behavior by leveraging datasets like Moral Integrity Corpus (MIC) and ProsocialDialog. Experimental results on several dialog datasets demonstrate the effectiveness of our approach in generating socially appropriate responses.

Large Language Models are successfully adopted in software engineering, especially in code generation. Updating these models with new knowledge is very expensive, and is often required to fully realize their value. In this paper, we propose a novel and effective model editing approach, \textsc{MENT}, to patch LLMs in coding tasks. Based on the mechanism of generative LLMs, \textsc{MENT} enables model editing in next-token predictions, and further supports common coding tasks. \textsc{MENT} is effective, efficient, and reliable. It can correct a neural model by patching 1 or 2 neurons. As the pioneer work on neuron-level model editing of generative models, we formalize the editing process and introduce the involved concepts. Besides, we also introduce new measures to evaluate its generalization ability, and build a benchmark for further study. Our approach is evaluated on three coding tasks, including API-seq recommendation, line-level code generation, and pseudocode-to-code transaction. It outperforms the state-of-the-art by a significant margin on both effectiveness and efficiency measures. In addition, we demonstrate the usages of \textsc{MENT} for LLM reasoning in software engineering. By editing the LLM knowledge with \textsc{MENT}, the directly or indirectly dependent behaviors in the chain-of-thought change accordingly and automatically.