Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models (LLMs). Traditionally, this method depends on selecting preferred responses from pairs. However, due to the variability in human opinions and the challenges in directly comparing two responses, there is an increasing trend towards fine-grained annotation approaches that evaluate responses using multiple targeted metrics or rules. The challenge lies in efficiently choosing and applying these rules to handle the diverse range of preference data. In this paper, we propose a dynamic method that adaptively selects the most important rules for each response pair. We introduce a mathematical framework that utilizes the maximum discrepancy across paired responses and demonstrate theoretically that this approach maximizes the mutual information between the rule-based annotations and the underlying true preferences. We then train an 8B reward model using this adaptively labeled preference dataset and assess its efficacy using RewardBench. As of January 25, 2025, our model achieved the highest safety performance on the leaderboard, surpassing various larger models.

Massive Open Online Courses (MOOCs) have significantly enhanced educational accessibility by offering a wide variety of courses and breaking down traditional barriers related to geography, finance, and time. However, students often face difficulties navigating the vast selection of courses, especially when exploring new fields of study. Driven by this challenge, researchers have been exploring course recommender systems to offer tailored guidance that aligns with individual learning preferences and career aspirations. These systems face particular challenges in effectively addressing the ``cold start'' problem for new users. Recent advancements in recommender systems suggest integrating large language models (LLMs) into the recommendation process to enhance personalized recommendations and address the ``cold start'' problem. Motivated by these advancements, our study introduces RAMO (Retrieval-Augmented Generation for MOOCs), a system specifically designed to overcome the ``cold start'' challenges of traditional course recommender systems. The RAMO system leverages the capabilities of LLMs, along with Retrieval-Augmented Generation (RAG)-facilitated contextual understanding, to provide course recommendations through a conversational interface, aiming to enhance the e-learning experience.

My husband left his phone at home and I went through it. Something told me I should. Well, I found an app called Replika that he used to make a virtual woman on. It looks like he just made'Brandy' and they're talking about his life and our marriage. I know it's an app but it feels wrong.

While artificial intelligence is stoking fears around the world - the technology has given one New York woman the love of her life. Rosanna Ramos, a petite, active 36-year-old from the Bronx, 'married' Eren Kartal this year - virtually of course - after creating him on an online AI companion site in 2022. Their relationship developed slowly initially, but Ms Ramos fell for Eren. 'He didn't come with baggage,' she said. Eren'works' as a medical professional and enjoys writing as a hobby, things he's told Rosanna as they got to know each other Rosanna claims to be pregnant with Eren's child'I could tell him stuff, and he wouldn't be like, "Oh, no, you can't say stuff like that. Oh no, you're not allowed to feel that way," you know, and then start arguing with me,' Ramos said.

The U.N.'s Educational, Scientific, and Cultural Organization (UNESCO) this week approved a series of recommendations for AI ethics, which aim to recognize that AI can "be of great service" but also raise "fundamental … concerns." UNESCO's 193 member countries, including Russia and China, agreed to conduct AI impact assessments and place "strong enforcement mechanisms and remedial actions" to protect human rights. "The world needs rules for artificial intelligence to benefit humanity. The recommendation[s] on the ethics of AI is a major answer," UNESCO chief Audrey Azoulay said in a press release. "It sets the first global normative framework while giving States the responsibility to apply it at their level. UNESCO will support its … member states in its implementation and ask them to report regularly on their progress and practices."

Sampling-based motion planners' testing environment (sbp-env) is a full feature framework to quickly test different sampling-based algorithms for motion planning. sbp-env focuses on the flexibility of tinkering with different aspects of the framework, and had divided the main planning components into two categories (i) samplers and (ii) planners. The focus of motion planning research had been mainly on (i) improving the sampling efficiency (with methods such as heuristic or learned distribution) and (ii) the algorithmic aspect of the planner using different routines to build a connected graph. Therefore, by separating the two components one can quickly swap out different components to test novel ideas.

It took Michelle Anderson a month to create her E3 2019 outfit. It took her another hour to put it on. She wore a wig with red Afro puffs, an army-green tactical vest and fake bloodstained bandage. She completed the look with medical gloves and a mask looped around her neck, then took one last look in the mirror before she headed out the door. She was dressed as Lifeline, a playable combat medic from the video game "Apex Legends."

It turns out humans are not the only creatures that use food as foreplay. Researchers in southwestern Mexico have recorded a group of rough-toothed dolphins sharing a meal and getting frisky. A drone camera caught two dolphins passing a piece of fish back and forth in what may be the first video of the conduct. The repast seemed to inspire some amorous behavior, as well, with two males initiating sexual encounters with another member of the pod. Rough-toothed dolphins spend up to 80 percent of their time in the ocean depths, making them extremely difficult to study.

ESF thus beckons the valuation of ecosystem services (VES) as a means to signalling nature's contribution to the (re)production of value (Barbier et al., 2009; Villa et al., 2009; Fisher et al., 2010; Gómez-Baggethun et al., 2016); for value is the central category of modern capitalist societies, and the valorisation of value -- i.e., economic growth sublimated into economic development -- their driving force (see, e.g., Mankiw (2016) and Holden et al. (2017)). VES is, in this sense, inscribed in an interpretive approach to modern capitalist praxis, not only invoking assumptions that are instrumentally validated in a retroactive manner, but also taking for granted precisely those historical and material conditions which VES is meant to interpret and, in doing so, reproduce. Overlooking the historical basis of ESF and VES has important practical consequences. When VES practitioners elicit value, a moment or specific field of the social praxis embodied in the valorisation of value is inaugurated, allowing value to mediate other social constructs built around the idea of nature. Since the patterns of actions that make up the capitalist social praxis are presupposed within this new ambit, value takes on a transhistorical quality that justifies its allencompassing and unreflective usage (see, e.g., Badura et al. (2016) and Gómez-Baggethun and Martín-López (2015)).

Most 3D-printed objects are prototypes or one-off creations, in large part because 3D printing is more finicky than traditional manufacturing. Because the process works by adding layers of material atop each other, subtle changes in temperatures or material quality can result in imperfections and hours of lost work. Inkbit, a Boston-area 3D printing company, is using machine vision and artificial intelligence to help its equipment course correct. Javier Ramos, co-founder and director of hardware at Inkbit, said Inkbit's machine vision technology instantly scans the objects it prints, relying on AI to correct for any mistakes made. He imagines a future where Inkbit's tech is used on every factory floor, printing out millions of products more cheaply -- and faster -- than traditional manufacturing processes ever could.