Shared conversations with Anthropic's Claude chatbot briefly appeared in Google search results because the pages lacked a noindex tag. Users said some chats contained crypto keys and legal questions. OpenAI made the same mistake last year. The article Shared Claude chats were reportedly showing up in search engines appeared first on The Decoder .
Hi HN, I've been working on ThorVG, an open-source vector graphics engine. It started as a lightweight SVG renderer and has gradually evolved into a rendering engine supporting SVG, Lottie, and modern GPU backends. This demo showcases the latest ThorVG 1.1 running entirely in the browser. Try it here: https://thorvg-janitor.vercel.app ThorVG v1.1: https://www.thorvg.org/post/thorvg-v1-1-rising-the-standard Comments URL: https://news.ycombinator.com/item?id=49066321 Points: 4 # Comments: 2
Hey HackerNews, I built this project over the last few weeks as a palette cleanser from a failed game launch. I wanted to learn a bit about AI/Neural-Networks and naively thought I could build a tiny maze-solving AI in a weekend with a 100% solve rate. Well - I couldn't, but I got pretty close. 14 Bytes total model size, and a 96.5% solve rate on unseen mazes. Trained across 46 phases experimenting with different ideas to improve the model (better performance, smaller size). Its quite fun to wat
https://seaticket.ai/ Comments URL: https://news.ycombinator.com/item?id=49066066 Points: 2 # Comments: 0
Article URL: https://github.com/YoniRaviv/Relay Comments URL: https://news.ycombinator.com/item?id=49065903 Points: 1 # Comments: 0
<p> Orchestrate an army of coding agents with your voice. </p> <p> <a href="https://www.producthunt.com/products/heyzoku?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1207527?app_id=339">Link</a> </p>
Article URL: https://github.com/CyrusNuevoDia/skill-language-server Comments URL: https://news.ycombinator.com/item?id=49065738 Points: 1 # Comments: 0
<p>Research shows AI accounts are gaining millions of views on TikTok by spreading dubious health advice</p><p>Misleading health claims online pose a “huge danger to public safety”, experts have warned, after research has shown that AI-generated doctors are gaining millions of views on TikTok by spreading dubious health advice.</p><p>The British Medical Association council deputy chair, Dr Emma Runswick, flagged the risks posed by AI accounts that “peddle medical myths and promote so-called mira
Hi HN, I've been working on StatsKit for the past year. It combines product analytics, feature flags, A/B testing, session replay and funnels into a single platform. https://statskit.ai Happy to answer any questions. Comments URL: https://news.ycombinator.com/item?id=49065644 Points: 1 # Comments: 0
It's a really, really big mess we've made. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.
Aug 13 2026 9am-12pm CDT / 10pm-12am SGT. A live tactical decision game with the creator of Tactical Decision Games, John Schmitt. TDGs are an accelerated expertise training format developed for the US Marines. Schmitt has kindly agreed to run a TDG and to take questions from the membership.
Hi guy, I am author of Spur , I want to share the Spur solver which is backed by z3 for neuro-symbolic reasoning, combining probabilistic language models with mathematical constraint solving The ideal here : LLM will give out constranst and translate the constranst to the z3 SMT language, then give out feedback loop between LLM model and neuro-symbolic reasoning to give out better reasioning looking for feedback and comments from HNs Thanks and best regards Kevin Comments URL: https://news.ycomb
arXiv:2607.21596v1 Announce Type: new Abstract: Large language model agents increasingly solve complex tasks by constructing inference-time workflows that combine reasoning, tool use, and code execution. While such workflows enable flexible problem solving, the useful procedures discovered during execution are often transient: they help solve the current task but are not retained in a form that can systematically benefit future tasks. We present FlowEvo, a training-free framework that compiles s
arXiv:2607.21600v1 Announce Type: new Abstract: Multimodal large language models introduce attack surfaces absent in unimodal systems: adversaries can distribute malicious intent across modalities to evade unimodal safeguards. This motivates using cross-modal consistency as a detection signal rather than inspecting each modality in isolation. Our key observation is that benign inputs induce compatible predictive behavior from text-only and vision-only reasoning that stabilizes when fused, wherea
arXiv:2607.21602v1 Announce Type: new Abstract: Accurate latency prediction is critical for deploying large language models (LLMs) on heterogeneous edge devices, where inference latency is affected by model architecture, prompt behavior, runtime backend, hardware utilization, dynamic voltage and frequency scaling (DVFS), and thermal variation. This paper presents a runtime-aware latency prediction framework for deployment-oriented LLM selection. The framework represents each inference request as
arXiv:2607.21604v1 Announce Type: new Abstract: Memory-augmented LLM agents maintain context across hundreds of interactions through agentic memory systems that actively curate retrieved content with LLM-generated metadata such as summaries, keywords, and tags. From an inference cost standpoint, every retrieval triggers a full re-encoding of these structured memory units into Key-Value (KV) states, which dominates prefill latency. Existing training-free KV reuse methods mitigate this by selectiv
arXiv:2607.21606v1 Announce Type: new Abstract: Recent advances in powerful text-to-image generation models have made it increasingly important to develop test-time methods that modify the sampling trajectory to produce images more faithful to complex compositional prompts. We present TILT, a training-free framework for compositional text-to-image generation via test-time reward alignment. We interpret compositional failures as overlap modes between joint and single-concept distributions, and de
arXiv:2607.21607v1 Announce Type: new Abstract: Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of training from solving long-range tasks. When we deploy GNNs on new graphs, there is currently no inexpensive way to know, before training begins, whether the graphs' structures will allow information to travel far enough between distant nodes. We address this gap by proposing Spectral Flow Certificates (S
arXiv:2607.21609v1 Announce Type: new Abstract: Although structured workflows empower Large Language Models (LLMs) to tackle complex problems, automating their creation is severely hindered by a vast combinatorial search space, frequently resulting in inflexible and resource-heavy offline training dependencies. To address this, we conceptualize workflow generation as an intertwined topology-and-execution search paradigm, where the broader topological layer dictates subtask boundaries and lower-l
arXiv:2607.21612v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods like LoRA have become the default for adapting large language models, succeeding across instruction following, style transfer, and factual adaptation. We show that for procedural knowledge--the ability to follow multi-step procedures with conditional branching through to terminal states--LoRA fails to match full fine-tuning at the ranks where it retains its efficiency advantage. In a systematic ablation (r =
arXiv:2607.21613v1 Announce Type: new Abstract: We investigate where and how transformer-based language models commit to predictions in multiple-choice question answering. We identify the _Hard Decision Layer_ (HDL), a natural architectural property where answer option rankings stabilize abruptly during inference. Empirical validation across four language models (Qwen, Llama, Granite, Mistral) and four benchmark datasets demonstrates consistent HDL emergence without learned routing policies. We
arXiv:2607.21614v1 Announce Type: new Abstract: Entity resolution (ER) typically relies on pairwise similarity comparisons between records, which limits its ability to capture indirect relationships present in demographic occupancy data. An important indirect pattern arises from household movement, where multiple individuals relocate together across addresses, but detecting such patterns is difficult due to mixed-format records, noise, duplication, and the absence of stable identifiers. This pap
arXiv:2607.21615v1 Announce Type: new Abstract: The rapid deployment of generative AI has amplified the critical need for Training Data Attribution to ensure transparency and accountability. However, current parametric approaches require computationally prohibitive access to model weights, while similarity-based methods ignore deep structural context. We propose a novel probabilistic framework that operates entirely in a black-box setting. Our method fuses continuous feature similarities with di
arXiv:2607.21616v1 Announce Type: new Abstract: Conventional wisdom suggests that reasoning models fail when problems exceed their capabilities. However, we find that frontier reasoning models sometimes possess the necessary capabilities to solve problems but fail due to premature self-doubt -- a phenomenon informally known as context anxiety. We provide the first systematic study of context anxiety, demonstrating that it arises, in part, from a model's inability to accurately estimate the token
arXiv:2607.21618v1 Announce Type: new Abstract: Modern data migration relies on JSON configuration to define data connection, pipeline logic, and orchestration behavior. This requires domain knowledge from users and is time-consuming and error-prone. In this paper, we present LeafData, an agentic system that converts user intent into validated and executable JSON configuration for data migration. Specifically, LeafData comprises a frontend chatbot and the backend service. The chatbot incremental
arXiv:2607.21620v1 Announce Type: new Abstract: Personalized text generation requires models to capture user-specific writing styles from historical data. Existing approaches based on retrieval, parameter-efficient fine-tuning, or activation steering either introduce inference and storage overhead or struggle to separate stylistic signals from semantic content. We propose GLASS, a training-free framework for personalized generation via Global-Local Activation Steering with Sparse priors. GLASS u
arXiv:2607.21624v1 Announce Type: new Abstract: Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks. On-device fine-tuning of transformer models offers a privacy-preserving path to personalized AI, yet remains inefficient on mobile GPUs due to severe memory constraints and frequent layout transformations in attention mechanism during training. Existing mobile training frameworks either use unified layouts for forward and backward passes
arXiv:2607.21625v1 Announce Type: new Abstract: We study the problem of decision-making from long-form, temporally structured text using large language model (LLM) agents. Standard retrievalaugmented generation (RAG) pipelines fragment chronological context into isolated snippets, discarding the temporal structure that is often critical for correct downstream decisions. We introduce TLM (Trajectory Language Model), a closed-loop agentic framework that iteratively refines the evidence set using S
arXiv:2607.21626v1 Announce Type: new Abstract: We study whether Group Relative Policy Optimization (GRPO) can fine-tune small language models for simulated quadrotor continuous-control tasks. In our benchmark, vanilla GRPO fine-tuning of Qwen-0.5B for 25 Hz quadrotor velocity control collapses to the trivial zero action: 0 percent success rate, with entropy falling from 0.35 to 0.03 within 60 steps. Two ablations - removing the jerk-penalty term and removing the KL anchor to the pretrained prio
arXiv:2607.21627v1 Announce Type: new Abstract: End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally. We identify Role Drift, a failure mode in which modules preserve or improve end-task performance while deviating from their assigned roles through role-violating shortcuts that remain invisible to system-level evaluation. To make role drift observable and controllable, we propose Role Anchor, a regulariz
arXiv:2607.21628v1 Announce Type: new Abstract: Simulation-to-reality translation must bridge the appearance gap between synthetic and real domains while preserving structural and semantic consistency. Conditioning-based methods achieve spatial alignment but introduce computationally expensive control modules. Paired-data methods achieve realism but rely on complex synthesis pipelines, often altering scene geometry and semantics. Training-free editing methods avoid both constraints but lack a le
arXiv:2607.21659v1 Announce Type: new Abstract: AI has begun to write systems code: agents now synthesize, verify, and deploy system components. Despite this shift, "AI-native" remains a marketing term with no precise technical definition. This paper gives it one. We define AI-nativeness along a single axis---authority over the system's own decisions rather than by the capability of the underlying AI models. Building on a decision-level model of a system, we distinguish occupancy (who executes a
arXiv:2607.21694v1 Announce Type: new Abstract: We present Oxygen-TryOn, a unified foundation model for any-item virtual try-on. Rather than repurposing a general-purpose image editor, Oxygen-TryOn is fashion-native, built for try-on through a dedicated data engine and try-on-specific training. Given one or more reference items (clean product shots or in-the-wild worn-on photos) and a single target subject image, it synthesizes a photorealistic image of the subject wearing the items across virtu
arXiv:2607.21787v1 Announce Type: new Abstract: Medical ultrasound (US) image segmentation faces significant challenges due to speckle noise, low-contrast boundaries, acoustic shadowing, and acquisition variation across operators and clinical centers. Although encoder-decoder and transformer-based networks have achieved strong performance, many methods recover boundary details through dense decoders or larger backbones, which may still produce over-smoothed contours or unstable predictions under
arXiv:2607.21792v1 Announce Type: new Abstract: One-to-many facial identification is commonly used to match a probe image from surveillance video against a gallery of driver's licenses and/or booking photos. The algorithm's rank-one image from the gallery, or a human examiner's selection from the algorithm's top-ranked images, may then be placed in a photo lineup shown to a witness. Witness selection of the gallery image in the photo lineup may then lead directly to the person in the gallery ima
arXiv:2607.21848v1 Announce Type: new Abstract: Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry, into photorealistic videos for gaming and immersive content creation. These applications require long-horizon auto-regressive generation that continuously synthesizes new frames while preserving a persistent 3D world. Auto-regressive generators synthesize video chunk by chunk with a bounded KV cac
arXiv:2607.21881v1 Announce Type: new Abstract: Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and land-conversion analysis. This study presents a reproducible workflow for mapping farmland extent and visible boundaries from 1 m NAIP RGB imagery. Thirty-seven scenes spanning open cropland, peri-urban interfaces, semi-arid irrigation geometries, and fragmented mosaics were annotated in CVAT
arXiv:2607.21904v1 Announce Type: new Abstract: Image inpainting aims to reconstruct missing or corrupted regions of an image while preserving as much as possible, visual and semantic consistency. In medical imaging, this task is particularly important because artifacts, missing information, and pathological alterations can compromise diagnostic reliability and downstream clinical applications. Recently, diffusion models have emerged as state-of-the-art generative approaches for medical image in
arXiv:2607.21973v1 Announce Type: new Abstract: Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central problem. Prompt-based adaptation, including Visual Prompt Tuning (VPT), provides a lightweight way to specialize these models, but its layer-wise behavior remains poorly understood: performance is sensitive to prompt depth, placement, and task distribution, and gains on standard in-domain benchmarks
