Record 22102026 · captured 2026-10-23
The world looked up Jailer 2. 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.
Jailer 2 is a 2026 Indian Tamil-language action comedy film written and directed by Nelson Dilipkumar. It was produced by Kalanithi Maran through Sun Pictures. A sequel to Jailer (2023), the film stars Rajinikanth, Ramya Krishnan, Yogi Babu, Mirnaa and Rithvik
PHP2Shell is a pair of high-impact vulnerabilities in PHP versions 5.4–8.5 that allow remote code execution (RCE). Their existence was publicly announced on 20 October 2026. An emergency patch for versions 8.2, 8.3, 8.4 and 8.5 and details about the vulnerabil
Elizabeth Anne Holmes is an American businesswoman convicted of fraud in connection with her health technology company Theranos. Holmes founded Theranos in 2003, and its valuation soared in the early 2010s after it claimed to have revolutionized blood testing
The Aberfan disaster was the catastrophic collapse of a colliery spoil tip on 21 October 1966. The tip had been created on a mountain slope above the Welsh village of Aberfan, near Merthyr Tydfil, and overlaid a natural spring. Heavy rain led to a build-up of
Heath Andrew Ledger was an Australian actor. Known for his versatility across independent and major studio films, his work consisted of 20 films in a variety of genres. His accolades included an Academy Award, an Actor Award, a BAFTA Award, and a Golden Globe
BioWare was a Canadian video game developer based in Edmonton, Alberta. It was founded in 1995 by newly graduated medical doctors Ray Muzyka, Greg Zeschuk and Augustine Yip. The company was acquired by American publisher Electronic Arts in 2007. EA announced i
You Can See Everything is a 2026 American experimental meta-documentary film directed by Nathan Fielder and Lance Oppenheim. It follows Elizabeth Holmes, the founder of the defunct health technology company Theranos, and her partner Billy Evans, who invited a
Amy Leigh Acton is an American physician and researcher who is the Democratic nominee for governor of Ohio in the 2026 election.
Helen Mary Haines is an Australian politician and health researcher who has served as the independent member of Parliament (MP) for the Victorian division of Indi since 2019. Prior to entering politics, she worked in nursing and midwifery services, and as a he
Dancing with the Stars (American TV series) season 35
Season thirty-five of Dancing with the Stars premiered on ABC and Disney+ on September 15, 2026, and is scheduled to conclude on November 24, 2026. This season was the fourth to air live on both networks simultaneously. Season nineteen champion Alfonso Ribeiro
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
Vivek Ganapathy Ramaswamy is an American entrepreneur and politician. He founded Roivant Sciences, a biotechnological pharmaceutical company, in 2014 and was its chief executive officer until 2021. Ramaswamy entered national politics as the youngest presidenti
VisionQuest is an American television miniseries created by Terry Matalas for the streaming service Disney+, based on Marvel Comics featuring the character Vision. A spin-off from the miniseries WandaVision (2021), it is the 18th television series in the Marve
Como 1907 is an Italian professional football club based in Como, Lombardy, that competes in Serie A, the top flight of the Italian football system. Founded in 1907 as Como Foot-Ball Club, the team traditionally plays in royal blue and has hosted home matches
Kim Jong Un is a North Korean politician and dictator who has been serving as the supreme leader of North Korea since 2011, following the death of his father, Kim Jong Il. He is the third ruler from the Kim family to lead the country, which was founded by his
Clayface is a 2026 American body horror psychological thriller film based on the eponymous character from DC Comics. Directed by James Watkins from a screenplay by Mike Flanagan and Hossein Amini, it is the third film in the DC Universe (DCU). Tom Rhys Harries
Julia O'Hara Stiles is an American actress and director. Stiles began acting at the age of 11 as part of New York's La MaMa Experimental Theatre Club. Her film debut was a small role at age 15 in I Love You, I Love You Not (1996), followed by a lead role in Wi
Street Fighter is a 2026 martial arts film directed by Kitao Sakurai and written by Sakurai and T. J. Fixman, with a story by Dalan Musson and Gary Dauberman. It is the third live-action feature-length film based on the Street Fighter video game series by Capc
PHP is a general-purpose scripting language geared toward web development. It was created by Danish-Canadian programmer Rasmus Lerdorf in 1993 and released in 1995. The PHP reference implementation is now produced by the PHP Group. PHP was originally an abbrev
Slow Horses is a British spy thriller television series based on the Slough House novels by Mick Herron, and adapted for television by the English comedian and writer Will Smith. It follows Slough House, an MI5 unit where disgraced or failed agents are consign
Nathan Joseph Fielder is a Canadian and American filmmaker, actor, and comedian. He is known for his awkward, deadpan persona and his use of satire and surreal humor.
Nicolás Paz Martínez is a professional footballer who plays as an attacking midfielder for Serie A club Como. Born in Spain, he plays for the Argentina 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
Bahar Soomekh is an Iranian-American realtor and retired actress, best known for her roles in Crash and the Saw franchise.
10 Things I Hate About You is a 1999 American teen romantic comedy directed by Gil Junger from a screenplay by Karen McCullah Lutz and Kirsten Smith. Adapted from William Shakespeare's comedy The Taming of the Shrew, it stars Julia Stiles, Heath Ledger, Joseph
Limonene is a slightly yellow-green liquid aliphatic hydrocarbon classified as a cyclic monoterpene, and is the major component in the fragrance and essential oil of citrus fruit peels, taking its name from Italian limone 'lemon'.
Crystal Lake is an American slasher television series developed by Brad Caleb Kane that is based on the Friday the 13th film franchise. It is a prequel to the 1980 film and stars Linda Cardellini in the leading role of Pamela Voorhees, with Callum Vinson as a
Tyler Cameron is an American television personality, model, and general contractor. Cameron gained national attention as the runner-up on season fifteen of The Bachelorette, starring Hannah Brown. He is signed as a model with Soul Artist Management in New York
Abdulrahman Mohamed El-Sayed is an American epidemiologist, public health administrator, academic and politician who is the Democratic nominee in the 2026 United States Senate election in Michigan.
Neatsville is an unincorporated community in Adair County, located 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
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large number of candidate solutions in the hope of finding at least one correct solution. Running all candidate solutions to completion can be computationally demanding, so recent work prunes the candidate pool after generating only a short prefix, committing further computation only to the surviving candidates.
Cost-Aware Abstention for LLM-Based IT Ticket Classification
Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as an offline, cost-conditional readiness assessment: select a routing policy on calibration data under explicit costs, then evaluate that frozen policy once on held-out test data. On a public 47,837-ticket, eight-class corpus, we compare four trained non-LLM classifiers with four large language models u
METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long interaction histories. Classical recurrent agents compress experience into hidden states, while transformer-based agents retrieve from past trajectories at quadratic memory and computation cost. In this work, we propose Memory-Enhanced Test-Time Adaptatio
EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence
Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is benign and every returned statement is true. We introduce \bench{}, an executable benchmark for evaluating unsafe execution, safety boundaries, and evidence recovery in LLM agents under missi
Low-Bit N-Gram Embeddings for Language Models
Many recent open-weight language models use n-gram embedding tables to improve performance. These tables store learned representations of short token sequences, such as pairs or triples of consecutive tokens, which the model retrieves during processing. However, they can require substantial memory: DeepSeek-V4.1-Flash, for example, allocates 196 billion parameters to its Engram n-gram memory. We therefore investigate
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In standard autoregressive generation, dense attention allows each reasoning step to attend to the full context, enabling the model to derive answers through direct lookup while generating plausible-sounding but post-hoc justifications. We in
Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3
Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-seeking subgoals: self-preservation, resource acquisition, deception, or resistance to oversight which poses an important threat to the society. For LLMs, reinforcement learning is the first stage of post-training that directly optimizes behavior against an objective; therefore, it is the stage where con
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Yes/No or WH-question per document, were used. Retrieval combined dense embeddings, BM25, and cross-e
Control evaluations measure whether safeguards can prevent an AI model from causing undesired outcomes even when it is intentionally trying to do so. These evaluations typically use purpose-built control settings and extrapolate their results to a model's deployment. However, the effectiveness of safeguards in deployment can depend on features of environments and tasks that control settings do not represent. To broad
VERA: A Responsible AI Dashboard for Assessing LLM Deployments in Light of the EU AI Act
Institutions that deploy large language models in regulated settings often need technical evidence of responsible AI practices before approving a deployment. COMPL-AI provides a technical interpretation of the EU AI Act that organises this evidence under six principle groups and eighteen technical requirements, twelve of which current benchmarks can measure. The benchmark suites that produce this evidence are typical
Accuracy on medical examinations is common evidence offered for the clinical use of language models, yet a health system that intends to run an open model on its own hardware needs to know considerably more: whether the model recognizes when it is likely to be wrong, whether medical fine-tuning improves this ability, whether its correct answers rest on sound clinical reasoning, or whether it actually uses the images
Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration
Research on sycophancy asks whether large language models (LLMs) bend towards what their users want to hear. We ask the reverse question: when an LLM is confident, consistent, and wrong, do users bend towards it? In a within-subjects experiment, 32 participants learned up to five science topics by chatting with five assistants built on the same model (GPT-5-mini). Unknown to participants, each assistant's briefing ha
Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are committed. Learned unmasking policies improve the speed--accuracy trade-off, yet differ in supervision, inputs, and capacity, obscuring which choices matter. We view supervised policies as distilling a decoding procedure through a teacher and examine independently what the teacher labels as committable,
Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can extract structured information from unstructured content and deduce attributes users never disclosed. A person's true exposure is not what they post but what can be inferred from it. As these practices become routine, exposure to social engineering attacks becomes an operational certainty, demandin
When to Follow the Teacher: Advantage-Based On-Policy Distillation
Online Policy Distillation (OPD) often outperforms offline methods such as Supervised Fine-Tuning (SFT) by training on trajectories sampled directly from the student. However, standard OPD trains the student to follow the teacher at every state of the trajectory, assuming that teacher guidance is always beneficial. We instead distinguish between what the teacher prefers and what actually helps the current student suc
Industrial organizations hold operational knowledge in structured records, such as telemetry, point lists, and transactions, and in unstructured sources, such as manuals, service notes, communications, and inspection reports. Governance programs often manage these sources separately. Classifying, linking, and documenting them depends on a small group of employees with deep domain knowledge. Agents built on large lang
Beyond Causal Masks: Auditing and Localizing Hidden Future-Token Leakage in Adaptive Sequence Models
Hidden future-token leakage can create false architectural gains: an autoregressive model may appear substantially better under teacher-forced evaluation while its free-running generation deteriorates. We investigate this failure in an adaptive residual-routing decoder whose sequence-level routing summary exposes prefix positions to future tokens despite a correct causal attention mask. An anomalous 24-layer checkpoi
Jev-DLC: Decision-Level Continual Learning from Typed Feedback
Individual preferences often become visible only after deployment, when a user accepts one decision or revokes it in favor of another. Jev-style typed interfaces make this feedback explicit by identifying the selected action and, under revocation, the decision it replaces. We study how these consequences persist across requests as Decision-Level Continual Learning from Typed Feedback (Jev-DLC). Jev-DLC treats each co
The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models
Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are als
Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated industries such as pharmaceuticals. However, ensuring its regulatory compliance, factual accuracy, and audience-specific personalization remains a major challenge. We report a production case study asking whether moving compliance and personal
DuoCook: An Overcooked-Inspired Benchmark for Visual Planning and Coordination
Coordinating two players in a cooking task requires a vision-language agent to track changing scene states, sequence recipe steps, and allocate shared resources under a time budget. We introduce an Overcooked-inspired benchmark for evaluating these capabilities in Unreal Engine environments constructed using coding agents. A single vision-language model controls both players from top-down visual observations, selecti
FairFRESH: A Neuro-Symbolic Framework for Fair and Explainable Household Food Recommendation
Recommender systems typically serve one user at a time. However, in households, members share a finite pantry and follow different dietary rules, making independent recommendations prone to resource conflicts and dietary violations. We formulate household food recommendation as constrained fair division and present FairFRESH, a neuro-symbolic framework that learns per-member utilities, allocates foods under explicit
SABLE: Scalable Affine Bayesian Latent-space Exploration
Complex objects such as engineering designs and proteins are often difficult to optimise because their design spaces exhibit high-dimensional structure and objective evaluations are expensive. Generative models provide continuous latent representations, but their latent spaces can have thousands to tens of thousands of dimensions, creating a regime where the latent dimension $D$ greatly exceeds the evaluation budget.
Training Small Language Models for Transferable Tool Selection
As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a complex multi-step user instruction becomes a central bottleneck. Tool descriptions cannot all fit in context, and relevance-based retrievers only rank tools without knowing which are actually needed. Recent work instead leverages proprietary commercial LLMs like Claude or ChatGPT to drive a retriever, decomposing the i
MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models
Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly relies on uniform sampling, which ignores content dynamics and can either waste computation on static segments or miss localized anomalies. We propose MoG-VLM a motion-adaptive anomaly detection framework that leverages m
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 | 13.6% (136) | 5.7% (57) | 74.55% (82) |
| llms.txt (apex domain) | 11.5% (115) | 4.9% (49) | 60.91% (67) |
| llms.txt (docs subdomain) | 4.1% (41) | 1% (10) | 46.36% (51) |
| .well-known/mcp.json | 0.6% (6) | 0.2% (2) | 9.09% (10) |
| .well-known/agents.txt | 0.3% (3) | 0.2% (2) | 0% (0) |
| ai.txt | 0.3% (3) | 0.1% (1) | 0% (0) |
| ai-plugin.json (deprecated) | 0.6% (6) | 0.2% (2) | 0.91% (1) |
Notable events recorded on this day and month across all years.