Record 17092026 · captured 2026-09-18
The world looked up Macklemore. 30 tracked subjects, 25 discussions, 25 papers. This record is frozen and will not change.
Complete record JSON
What the most people looked up, ranked by Wikipedia pageviews for that day.
Benjamin Hammond Haggerty, better known by his stage name Macklemore, is an American rapper. A native of Seattle, Washington, he started his career in 2000 as an independent artist releasing Open Your Eyes (2000), The Language of My World (2005), and The Unpla
Robert Hearth Kenneth Kraft is an American businessman. He is the chairman and chief executive officer (CEO) of the Kraft Group, a diversified holding company with assets in paper and packaging, sports and entertainment, real estate development, and a private
Lizzie Andrew Borden was an American woman who was tried and acquitted of the August 4, 1892 axe murders of her father and stepmother in Fall River, Massachusetts. No other individuals were charged with the murders, and Borden spent the remainder of her life i
Edward Christopher Sheeran is an English singer-songwriter. Born in Halifax, West Yorkshire, and raised in Framlingham, Suffolk, he began writing songs around the age of eleven. In early 2011, Sheeran independently released the extended play No.5 Collaboration
Joseph Junior Andreou O'Cearuill, commonly known as JJ Gabriel, is an English footballer who plays as a forward for Premier League club Manchester United.
Dancing with the Stars (American TV series) season 35
Season thirty-five of Dancing with the Stars will premiere on ABC and Disney+ on September 15, 2026. This season will be the fourth to air live on both networks simultaneously. Season nineteen champion Alfonso Ribeiro will return to host the installment, while
Jyothika Saravanan is an Indian actress and producer who primarily works in Tamil and Hindi films. She has received several accolades including a National Film Award, five Filmfare Awards South, six Tamil Nadu State Film Awards and Kalaimamani Award. Jyothika
The following notable deaths occurred in 2026. Names are reported under the date of death, in alphabetical order. A typical entry reports information in the following sequence:Name, age, country of citizenship at birth, subsequent nationality, what subject was
Widow's Bay is an American supernatural comedy horror television series created by Katie Dippold for Apple TV, and starring Matthew Rhys, Kate O'Flynn, Kevin Carroll, Dale Dickey, Kingston Rumi Southwick, and Stephen Root. The series is set in the fictional Ne
Resident Evil is a 2026 survival horror film that is the second reboot and eighth film overall in the Resident Evil film series, based on Capcom's Resident Evil video game franchise. It is directed by Zach Cregger and written by Cregger and Shay Hatten. The fi
Sydney Bernice Sweeney is an American actress. She gained early recognition for her roles in Everything Sucks!, The Handmaid's Tale, and Sharp Objects in 2018. She received wider acclaim for her performances in the drama series Euphoria (2019–2026) and the fir
Matthew Rhys is a Welsh actor. Known for portraying morally complex protagonists, he has received various accolades including four Primetime Emmy Awards, becoming the first and only actor to win in all three Lead Actor categories in Emmys history. He has also
The September 11 attacks, colloquially known as 9/11, were a coordinated series of suicide attacks perpetrated by the Islamic terrorist organization al-Qaeda against the United States in 2001. A total of 19 hijackers commandeered four commercial passenger airl
Harry Shum Jr. is an American actor and dancer. He is known for his roles as Mike Chang on the Fox television series Glee (2009–2015), Magnus Bane on the Freeform television series Shadowhunters (2016–2019), and Dr. Benson Kwan on the ABC television series Gre
List of Tim Curry performances
Tim Curry (1946–2026) was a British actor and singer who had numerous roles in films, television shows, video games, and audiobooks.
Neatsville is an unincorporated community in Adair County, in the U.S. state of Kentucky. It is located at the junction of Kentucky Route 206 and Kentucky Route 76. Its elevation is 705 feet (215 m). For unknown reasons, the town's name was spelled as Neetsvil
Hanuman Ansh is a 2026 Indian Hindi-language biographical film written, directed and produced by Vishal Chaturvedi under his banner, Swambhu Media Network. Serving as the first instalment of a trilogy, it is based on his book "Divine Detour: That Changed My Li
Killing of the Clancy children
On January 24, 2023, Lindsay Clancy fatally strangled her three children—five-year-old Cora, three-year-old Dawson, and eight-month-old Callan—at the family's home in Duxbury, Massachusetts, United States. She then attempted suicide by cutting her wrists and n
Joseph Delpesh O'Cearuill is a retired footballer who played as a defender. His previous clubs have included Barnet and St. Patrick's Athletic, and he has been capped by the Republic of Ireland.
Thomas Joseph Pelphrey is an American actor. He is known for playing the roles of Jonathan Randall on the CBS television series Guiding Light, Mick Dante on As the World Turns, Kurt Bunker on Banshee, Ward Meachum on Iron Fist, Ben Davis on Ozark, Perry Abbott
Jordan Taylor Hanson is an American musician best known as a member of the eponymous pop rock band Hanson. He sings both lead and back-up vocals, and plays keyboard, percussion, guitar, harmonica, and piano. Hanson was also lead singer of the supergroup Tinted
Marvel's Wolverine is a 2026 action-adventure game developed by Insomniac Games and published by Sony Interactive Entertainment. Based on the Marvel Comics character Wolverine, it is inspired by the long-running comic book mythology, while also deriving from v
Kaley Christine Cuoco is an American actress. She starred as Bridget Hennessy on the ABC sitcom 8 Simple Rules (2002–2005), Penny on the CBS sitcom The Big Bang Theory (2007–2019), and as the title character in the HBO Max comic thriller The Flight Attendant (
Raheem Shaquille Sterling is a professional footballer who plays as a winger. He is currently a free agent. Born in Jamaica, he has played for the England national team.
Ezra Frech is an American track and field athlete who competes in high jump, long jump and sprinting events. He is a two-time Paralympian, having competed at the 2020 Summer Paralympics and won two gold medals at the 2024 Summer Paralympics. He also won two si
Timothy James Curry was an English actor and singer who amassed more than 240 credits on screen and stage in a career which spanned nearly 60 years. Curry made his acting debut in the West End production of Hair (1968–1969) and gained wide recognition for port
General elections were held in Sweden on 13 September 2026 to elect the 349 members of the Riksdag, alongside municipal and regional elections. The incumbent government was a minority government led by Ulf Kristersson of the Moderate Party (M), Christian Democ
Lanterns is an American superhero television series created by Chris Mundy, Damon Lindelof, and Tom King for HBO, based on the DC Comics Green Lantern characters Hal Jordan and John Stewart. It is the third television series in the DC Universe (DCU). It featur
Anna's Archive is an open source search engine for shadow libraries that was launched by the pseudonymous Anna shortly after law enforcement efforts to shut down Z-Library in 2022. The site aggregates records from Z-Library, Sci-Hub, and Library Genesis (LibGe
Saravanan Sivakumar, known professionally as Suriya, is an Indian actor and film producer who primarily works in Tamil cinema. One of the highest-paid Tamil film actors, Suriya is considered as one of the finest actors of Indian cinema. Suriya has received num
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific training.Whether this paradigm is also safe, however, has not been asked. We evaluate coding agent under a safety constraint, where each task pairs a manipulation goal with an obstacle the robot must not touch. The
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades performance, many approaches to policy memory involve compressing historical information through expensive VLM queries in-the-loop to process only task-salient information. In this paper, we propose an alternative approach i
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation and therefore rely heavily on learned category-level shape priors. We present FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from a sparse, unordered set of pa
Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inference procedures. Advances in large language models offer a simpler starting point: even compact models can associate hex va
Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate classification of these syndromes are essential for timely diagnosis, individualized patient management, and targeted surveillance strategies for affected families. However, public endoscopic datasets are largely organized around the individual
Quantifying Overclaiming Propensity in Frontier LLM Agents
Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that work a user sees. We quantify the propensity of frontier agents to \emph{overclaim} task completion, a misrepresentation that can mislead the user. An agent overclaims when its final response contradicts information in its context. This definition requires no inference
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of individual components unclear. To enable component-level comparisons, we study this question with a lightweight coding harness whose execution loop is fixed while three components are var
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with privileged task skills, letting a skill-free student internalize them. This recipe, however, is undermined by two findings in agentic tasks: privileged information alone does not always make a teache
Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically incomplete: explicit discriminatory content is transformed rather than removed. We call this \emph{harm laundering}. Analysing 450,000 gender-directed completions across 15 models spanning GPT-2 through to GPT-5 (OpenAI GP
GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a rollout, different task stages may require different levels of action continuity, control precision, and closed-loop feedback, making a fixed horizon unable to accommodate changing control requirements. We propose \textbf{GeoAAC}, a geometry
Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstructured or frame-level representations. Their output is consequently difficult for a viewer to verify and steer toward individual preferences. We present the semantic action graph, a lightweight domain schema that represents a sports match as performer, action, recipient, moment, and state nodes connec
Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests on a sample of labeled units. We treat the evaluation set as a finite population and seek accurate point and interval estimates of each domain mean. Direct estimators, including prediction-powered inf
RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing retrieval-augmented generation (RAG) systems treat support cases as static documents and overlook their multi-stage, stateful nature. We introduce RAFT (Retrieval-Augmented Framework for Troubleshooting Agents), a stateful RAG framework that abstracts each closed histori
Large Language Models as Falsifiers for Cyber-Physical Systems
Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a robustness optimization problem, traditionally tackled with black-box search algorithms. In parallel, large language models (LLMs) have recently emerged as surprisingly effective optimizers when coupled with iterative prom
Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retrieval accuracy. We propose a novel framework of splitting any spreadsheet into interpretable chunks using cell role annotation. Our framework beats the state of the art, yet it faces a hard ceiling. Spreadsheets are fundamentally two-dimensi
Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Lens convergence and causal head-level attribution to autonomously discover optimal steering parameters. Across three scales (1B x 3, 2-3B x 2, and 7-9B x 4), our engine achieves 16.7 percentage-point improvement on spam at 1B (standard deviat
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as context but not as prediction targets. We ask whether this convention provides the best initialization for subsequent reinforcement learning. We introduce ActObs, which also supervises the observation tokens already present i
Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Supervised fine-tuning (SFT) on task-specific demonstrations provides a step toward deployment, but faces two persistent limitations: static data provide limited coverage of out-of-distribution states, and standard imitation objectives do not distinguish progr
Ownership in AI-Assisted Everyday Tasks
When does work done with AI still feel like ours? As AI becomes woven into everyday tasks, we must examine what happens to our sense of ownership and contribution when a machine shares in producing what we make. We report an exploratory qualitative survey in which participants were asked to describe two recent, self-selected tasks completed with AI: one that felt like their own and one that did not. We find that felt
Allen's interval algebra is a qualitative calculus for temporal relations, but its thirteen base relations are crisp predicates over exact interval boundaries. This is inadequate for temporal information from language, perception, databases, or uncertain histories, where times, durations, and boundaries are uncertain and expressions such as "just before" or "roughly during" have graded meaning. We develop the probabi
Chronicle: Cut-Point Replay for Regression Testing of LLM Agents
Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on tools that read changing state, and on a multi-step trajectory that a re-run rarely repeats. Record-and-replay makes a run reproducible, but existing agent tooling records runs only to trace or score them, not to test a code change against them. We
A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies
Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in which conventional deterministic layered control autonomy manages normal operations, while an invokable large language model (LLM) serves as a diagnostic and recovery planner when onboard anomaly detection identifies performance outside expected limits
Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus on components other than the inference engine itself (e.g., network proxies or code execution environments). However, th
Limits of Confidence in Diffusion
Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write from those same distributions. For domains of general interest (pixels, phonemes, or words) there are inherent dependencies between tokens. We show that a step matches the training distribution only whe
Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control
Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. First-order policy gradients (FoPG) reduce training cost through differentiable simulation, but local optimization can converge to unintended contact patterns. To address this shortfall, we propose Sampling-Guided Policy Search (SGPS), which couples re
Origins publishing files written for machines rather than people. Measured against a frozen cohort, so a change in the number means a change in adoption.
| Signal | Web head Tranco top 1,000 n=1,000 | Web tail sampled to rank 100k n=1,000 | AI-native model & dev platforms n=110 |
|---|---|---|---|
| Any agent-facing signal | 12.2% (122) | 5.6% (56) | 73.64% (81) |
| llms.txt (apex domain) | 9.7% (97) | 4.7% (47) | 60% (66) |
| llms.txt (docs subdomain) | 4% (40) | 1% (10) | 43.64% (48) |
| .well-known/mcp.json | 0.6% (6) | 0.3% (3) | 8.18% (9) |
| .well-known/agents.txt | 0.3% (3) | 0.2% (2) | 0% (0) |
| ai.txt | 0.2% (2) | 0.1% (1) | 0% (0) |
| ai-plugin.json (deprecated) | 0.7% (7) | 0.2% (2) | 0.91% (1) |
Notable events recorded on this day and month across all years.