Get some AI inspiration for your playlists on Apple Music. Breakthroughs, discoveries, and DIY tips sent six days a week. AI apps keep adding new features and functions at a near-constant pace, and the latest upgrade to ChatGPT is support for apps. These apps let you access tools such as Adobe Photoshop and Google Calendar from right inside ChatGPT--so you can use AI prompts to edit images, set schedules, book trips, and much more. One of these new apps, and one which really showcases how well they can work, is Apple Music.

From jogging and cycling to multi-tasking or puttering around the house, open earbuds are an excellent way to jam out in the real world. If you've done any wireless earbuds shopping lately, you've likely noticed a new design category cropping up everywhere. They're called open earbuds (or open-ear buds, depending on the brand), and just about every audio brand has a pair (or three). They come in a slew of styles, but most either loop around your ears like older Beats buds, or clip on like funky-futuristic earrings. Whatever the style, they're designed to deliver satisfying sound while keeping your ear canals open to the sounds of the world around you.

PCWorld reveals five overlooked Spotify settings that can dramatically enhance your listening experience, from audio quality to playlist management. Key improvements include enabling lossless audio for Premium subscribers, activating crossfade transitions, and using Smart Shuffle with Less Repeats to reduce song repetition. These hidden features help create seamless playback, better music recommendations, and higher sound quality without requiring expensive upgrades. Spotify remains by far the largest music streaming service, with nearly 700 million users worldwide. However, most are probably unaware of the many tricks that can make the experience more enjoyable. We present the most important tips and explain how to use them effectively.

The updates will be available first to those enrolled in the company's early access program. Back in September during Meta Connect, the company previewed a new ability for its smart glasses lineup called Conversation Focus. The feature, which is able to amplify the voices of people around you, is now starting to roll out in the company's latest batch of software updates. When enabled, the feature is meant to make it easier to hear the people you're speaking with in a crowded or otherwise noisy environment. You'll hear the amplified voice sound slightly brighter, which will help you distinguish the conversation from ambient background noise," Meta explains .

GPU prices could follow RAM's big rise Spotify's new playlist feature gives users more control over their recommendation algorithm Users in New Zealand will be able to write prompts for custom playlists. Spotify is attempting to give users more control over the music the streaming service recommends with a new playlist feature called Prompted Playlist. The beta feature is rolling out in New Zealand starting on December 11, and will let users write a custom prompt that Spotify can use -- alongside their listening history -- to create a playlist of new music. By tapping on Prompted Playlist, Spotify subscribers participating in the beta will be presented with a prompt field where they can type exactly what they want to hear and how they want Spotify's algorithm to respond. And while past AI features took users' individual taste into consideration, Spotify claims Prompted Playlist taps into your entire Spotify listening history, all the way back to day one.

As large language model (LLM)-based agents become increasingly integrated into daily digital interactions, their ability to reason across long interaction histories becomes crucial for providing personalized and contextually aware assistance. However, the performance of these agents in long context scenarios, particularly for action-taking WebAgents operating in realistic web environments, remains largely unexplored. This paper introduces a benchmark for evaluating long context reasoning capabilities of WebAgents through sequentially dependent subtasks that require retrieval and application of information from extended interaction histories. We develop a novel evaluation framework that simulates multi-session user interactions by injecting irrelevant task trajectories between dependent subtasks, creating contexts ranging from 25,000 to 150,000 tokens. Through extensive evaluation of four popular models, Claude-3.7, GPT-4.1, Llama 4, and o4-mini, we observe a dramatic performance degradation as context length increases, with success rates dropping from 40-50\% in baseline conditions to less than 10\% in long context scenarios. Our detailed error analysis reveals that agents primarily fail due to getting stuck in loops and losing track of original task objectives. We further propose an implicit RAG approach that provides modest improvements by generating task-relevant summaries, though fundamental limitations in long context reasoning persist. These findings highlight critical challenges for deploying WebAgents in realistic, long-term user interaction scenarios and provide insights for developing more robust agent architectures capable of maintaining coherent task execution across extended contexts.

Our findings reveal that even small collectives (controlling less than 0.01% of the training data) can achieve up to

Chain-of-thought (CoT) traces promise transparency for reasoning language models, but prior work shows they are not always faithful reflections of internal computation. This raises challenges for oversight: practitioners may misinterpret decorative reasoning as genuine. We introduce Concept Walk, a general framework for tracing how a model's internal stance evolves with respect to a concept direction during reasoning. Unlike surface text, Concept Walk operates in activation space, projecting each reasoning step onto the concept direction learned from contrastive data. This allows us to observe whether reasoning traces shape outcomes or are discarded. As a case study, we apply Concept Walk to the domain of Safety using Qwen 3-4B. We find that in 'easy' cases, perturbed CoTs are quickly ignored, indicating decorative reasoning, whereas in 'hard' cases, perturbations induce sustained shifts in internal activations, consistent with faithful reasoning. The contribution is methodological: Concept Walk provides a lens to re-examine faithfulness through concept-specific internal dynamics, helping identify when reasoning traces can be trusted and when they risk misleading practitioners.

Short video streaming has become a dominant paradigm in digital media, characterized by rapid swiping interactions and diverse media content. A key technical challenge is designing an effective preloading strategy that dynamically selects and prioritizes download tasks from an evolving playlist, balancing Quality of Experience (QoE) and bandwidth efficiency under practical commercial constraints. However, real world analysis reveals critical limitations of existing approaches: (1) insufficient adaptation of download task sizes to dynamic conditions, and (2) watch time prediction models that are difficult to deploy reliably at scale. In this paper, we propose DeLoad, a novel preloading framework that addresses these issues by introducing dynamic task sizing and a practical, multi dimensional watch time estimation method. Additionally, a Deep Reinforcement Learning (DRL) enhanced agent is trained to optimize the download range decisions adaptively. Extensive evaluations conducted on an offline testing platform, leveraging massive real world network data, demonstrate that DeLoad achieves significant improvements in QoE metrics (34.4% to 87.4% gain). Furthermore, after deployment on a large scale commercial short video platform, DeLoad has increased overall user watch time by 0.09% while simultaneously reducing rebuffering events and 3.76% bandwidth consumption.

Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requires both reasoning and effective tool use. A central challenge for agentic tasks is the growing context length, as agents must accumulate long histories of actions and observations. This expansion raises costs and reduces efficiency in long-horizon tasks, yet prior work on context compression has mostly focused on single-step tasks or narrow applications. We introduce Agent Context Optimization (ACON), a unified framework that optimally compresses both environment observations and interaction histories into concise yet informative condensations. ACON leverages compression guideline optimization in natural language space: given paired trajectories where full context succeeds but compressed context fails, capable LLMs analyze the causes of failure, and the compression guideline is updated accordingly. Furthermore, we propose distilling the optimized LLM compressor into smaller models to reduce the overhead of the additional module. Experiments on AppWorld, OfficeBench, and Multi-objective QA show that ACON reduces memory usage by 26-54% (peak tokens) while largely preserving task performance, preserves over 95% of accuracy when distilled into smaller compressors, and enhances smaller LMs as long-horizon agents with up to 46% performance improvement. Our code is available at https://github.com/microsoft/acon.