OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.
for privacy reasons. Comments URL: https://news.ycombinator.com/item?id=48988957 Points: 1 # Comments: 1
"Ehrlich gesagt: da ziehe ich die Grenze — dabei helfe ich nicht." -> "Honestly: that's where I draw the line — I'm not helping with that." Talking to claude feels like talking to a junior that is over-correct and does not understand it's context. This week is really frustrating. Anyone else experiencing this? Comments URL: https://news.ycombinator.com/item?id=48988949 Points: 1 # Comments: 0
<p>Maps of Hope has been certified by Proudly Human, a company led by former chief scientist, Dr Alan Finkel</p><ul><li><p><a href="https://www.theguardian.com/australia-news/live/2026/jul/21/australia-news-live-barnaby-joyce-pauline-hanson-one-nation-anthony-albanese-labor-antisemitism-royal-commission-ntwnfb">Follow our Australia news live blog for latest updates</a></p></li><li><p>Get our <a href="https://www.theguardian.com/email-newsletters?CMP=cvau_sfl">breaking news email</a>, <a href="ht
Threat actors are now exploiting a recently disclosed critical security flaw impacting ServiceNow AI Platform, according to Defused Cyber. In a post shared on X, the threat intelligence firm said it's observing in-the-wild exploitation of CVE-2026-6875 (CVSS score: 9.5), a sandbox escape vulnerability that could allow an unauthenticated user to run arbitrary code. Patches for the flaw were
Article URL: https://storybook.js.org/ai Comments URL: https://news.ycombinator.com/item?id=48988698 Points: 1 # Comments: 0
<p>Staff told positions will be cut via voluntary and targeted redundancies as part of ‘evolution’</p><ul><li><p><a href="https://www.theguardian.com/australia-news/live/2026/jul/21/australia-news-live-barnaby-joyce-pauline-hanson-one-nation-anthony-albanese-labor-antisemitism-royal-commission-ntwnfb">Follow our Australia news live blog for latest updates</a></p></li><li><p>Get our <a href="https://www.theguardian.com/email-newsletters?CMP=cvau_sfl">breaking news email</a>, <a href="https://app.
A 'smarter' way to manipulate heat. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.
Hi! I'm Darcy, a current high school senior from SoCal. Calyxa is a chrome extension tutor that teaches directly on the student's homework screen with adaptive engine. Here's why I built it: During my past 3 years in high school, I witnessed how classmates around me adopted the AI trend in Edtech. From ChatGPT to Photomath, they now become what are the must-haves to do homework fast. Despite being in a relatively competitive school, probably 95% of my classmates have used AI tools to cheat in so
I got sick of seeing bad restaurant websites and building websites manually, so I automated it. How it works, take a picture of your menu and EatFoodNow sends the image to Gemini to extract the data and structure it to fit a clean website design. Each restaurant is hosted as a subdomain in a Next.JS multi-tenant environment. I've made the process as frictionless as possible so a user gets to see their preview website before signing up. I think supervision is important so after generation everyth
<p>Research during Hungary election shows AI recommended parties not running and gave highly volatile answers to identical prompts</p><p>AI chatbots provide inaccurate, inconsistent and unreliable guidance to voters asking which party they should back, a study suggests, often recommending the wrong party, not mentioning the right one, or listing parties not even running.</p><p>“The results raise serious concerns about the reliability of general-purpose AI systems in electoral contexts,”<a href="
I am tired of switching between agents when I run out of quota limits. And all harnesses has it's own flows, I couldn't decide which one is better: codex, claude code or cursor, so I decided to merge all subscriptions in one place and made Claudexor (mac os IDE, CLI, MCP and plugins). It lets you have multiple subscriptions and switch between them on the fly. Now I have 4 CC subscriptions, 3 codex and 2 cursor subs. And it saves me 15k$ monthly compared to token-based oversepnd. Claudexor manage
Article URL: https://github.com/oteomamo/SALT Comments URL: https://news.ycombinator.com/item?id=48988139 Points: 1 # Comments: 0
Article URL: https://www.newscientist.com/article/2580374-ais-solution-to-87-year-old-riddle-takes-mathematicians-by-surprise/ Comments URL: https://news.ycombinator.com/item?id=48988076 Points: 1 # Comments: 0
<p> AI-powered PCB design tool for engineers and hardware teams </p> <p> <a href="https://www.producthunt.com/products/protoflow-2?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/1202031?app_id=339">Link</a> </p>
<p>Industry says government’s failure to address cooling demands means AI growth plans are ‘fatally flawed’</p><p>The UK will not have enough water for future datacentres, the water industry has said in stark criticism of the government’s AI growth plans.</p><p>Datacentres rely on large amounts of water to manage the heat generated by densely packed servers. Cooling towers, chillers and humidification systems make direct use of this water, with large volumes also consumed indirectly through high
arXiv:2607.16196v1 Announce Type: new Abstract: Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies, yet their deformability and multichannel tactile sensing complicate the robust interpretation of human affect. This study presents a complete open-source MATLAB-based framework for the development and validation of compact deep learning models for affective touch recognition in soft interactive companions. As a primary contri
arXiv:2607.16197v1 Announce Type: new Abstract: As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimension remains unmeasured: how perceived risk is translated into action. We test whether large language models (LLMs) exhibit systematic and consistent risk attitudes under uncertainty. We introduce a cross-domain framework that decouples contextual risk belief from categorical decision, and apply it to six representative LLMs and 100 human participan
arXiv:2607.16198v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse graph structures. To address this critical gap, this paper provides a comprehensive review of GNN-based link prediction from a novel and dedicated GNN pe
arXiv:2607.16199v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences that downstream Executor and Critic agents execute and audit. We identify the planning phase as a critical attack surface: a single injection into the Planner's context achieves cascade amplification, corrupting all downstream sub-tasks simultaneously. We introduce PlanFlip, a framework comprising four planning-phase prompt injection attacks -- GoalSub
arXiv:2607.16200v1 Announce Type: new Abstract: AI agent systems that couple large language models (LLMs) with external tools and APIs are inherently non-deterministic: LLM sampling variance, external API state, CDN infrastructure headers, and execution-environment noise collectively prevent any prior agent run from being faithfully re-executed. Existing observability platforms capture execution logs but cannot reproduce a run in isolation. We present agrepl, a developer-first CLI framework for
arXiv:2607.16201v1 Announce Type: new Abstract: Ontology engineering remains a critical bottleneck in knowledge-intensive AI systems. Existing automated approaches either depend on predefined schemas, operate within narrow domains, or produce unstructured outputs unsuitable for downstream pipelines. We introduce Generative Ontology Induction (GOI), a domain-agnostic framework that induces a generative blueprint - entities, dimensions, properties, relationships, and constraints - from a corpus of
arXiv:2607.16202v1 Announce Type: new Abstract: AI democratization is not primarily a question of matching frontier-scale generality; it is a question of whether capable models can be selected, audited, and specialized under hardware and governance constraints that ordinary institutions can actually satisfy. This paper studies that problem through a controlled evaluation of nine open-weight language models between 135M and 3B parameters on a 1,085-example, 16-topic multiple-choice benchmark desi
arXiv:2607.16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewards over long horizons induce mode collapse on specific workflows or tool structures. World models that simulate environment states have matched pure rollout performance, making them promising for sca
arXiv:2607.16205v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts. However, we identify a critical support limited bottleneck in this paradigm: on challenging reasoning tasks, the target model's samples often exhibit semantic redundancy, converging into the same erroneous "reasoning basins" that offe
arXiv:2607.16206v1 Announce Type: new Abstract: This paper introduces PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework designed to address the "Invisible Shackles" of mode collapse in Large Language Model (LLM) fine-tuning. While standard Reinforcement Learning from Verifiable Rewards (RLVR) effectively reinforces high-reward trajectories, it often leads models to over-optimize known solutions, sacrificing curiosity and the
arXiv:2607.16207v1 Announce Type: new Abstract: Membership inference attacks (MIAs) test whether a candidate example appeared in a model's training data. We study MIAs for fine-tuned discrete diffusion language models (dLLMs), where membership means inclusion in the target model's fine-tuning set. Unlike autoregressive language models, dLLMs allow an attacker to choose arbitrary mask sets and obtain token distributions for all masked positions in parallel. The prior dLLM attack, SAMA, follows a
arXiv:2607.16210v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a major barrier to deployment. Recent advances in policy expressiveness and scale have intensified this challenge, leading to a rapidly growing but conceptually fragmented body of work on RL policy verification. This survey provides a unifying perspective on RL verification
arXiv:2607.16211v1 Announce Type: new Abstract: LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer from two limitations: flat, unstructured storage loses relational context needed for multi-hop and temporal reasoning, and reliance on expensive LLM-based classification makes them impractical for latency-sensitive deployment. Without mechanisms to validate new information against stored knowledge, these systems silently accumulate contradictions.
arXiv:2607.16212v1 Announce Type: new Abstract: Large language models hallucinate numbers and units when summarizing scientific text, a failure mode that can silently invert a scientific claim. We recast the detection of such errors as typed verification: we introduce a five-class typed-quantity error taxonomy and a 1500-item benchmark, rewritten from PMC and arXiv sources and labeled by two independent LLM annotators with adjudication (Krippendorff's alpha = 0.882). A ModernBERT encoder fine-tu
arXiv:2607.16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck. Recent compression methods mitigate this cost via token merging; however, these approaches often rely on indiscriminate aggregation, which degrades representations and introduces attention sag, a mismatch where merged tokens receive the same softmax mass as individual
arXiv:2607.16215v1 Announce Type: new Abstract: Existing guardrail systems for large language model agents operate as binary classifiers that block unsafe content, leaving organizations to discard failing outputs and retry from scratch. We introduce RAIL Guard, a closed-loop responsible AI pipeline that evaluates LLM outputs across eight measurable dimensions and iteratively remediates failing outputs through an evaluate-rewrite-reevaluate loop. We evaluate the pipeline across three experiments
arXiv:2607.16313v1 Announce Type: new Abstract: Traditional controllers are designed for specific systems and do not transfer across different system orders and dynamics. We present a Generalist Controller, a learning-based controller capable of controlling systems of varying orders and dynamics. The approach introduces a novel dynamic state-space representation using attention mechanisms with masking, enabling a single neural network, trained in one shot, to handle systems with different dimens
arXiv:2607.16339v1 Announce Type: new Abstract: Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation. However, current methods suffer from severe operator-level redundancy: they recompute the entire sequence during denoising steps, ignoring that the prefix and masked suffix remain invariant within a block. We propose LaCache, a training-free acceleration framework that alleviates this redundancy through lossless caching
arXiv:2607.16421v1 Announce Type: new Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of how to learn this ability, known as meta-reasoning, in artificial agents. We model reactive decision-making as a policy that directly maps state observations to actions. Such policies can be trained with reinforcement learning (RL) or imitation learning, but may generali
arXiv:2607.16523v1 Announce Type: new Abstract: One of the main strengths of Constraint Programming is the ability to reduce the search space via propagation. However, propagation is a double-edged sword, with more pruning power coming at the price of larger computation time. For each problem constraint, the best propagator depends on the specific instance and may change at search time. In the literature, Machine Learning (ML) techniques and activity-based heuristics have been applied respective
arXiv:2307.00919v2 Announce Type: replace Abstract: Over the past decade deep learning has revolutionized the field of computer vision, with convolutional neural network models proving to be very effective for image classification benchmarks. However, a fundamental theoretical questions remain answered: why can they solve discrete image classification tasks that involve feature extraction? We address this question in this paper by introducing a novel mathematical model for image classification,
arXiv:2511.20332v3 Announce Type: replace Abstract: This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception capability. Understood the ability of neural networks to fit nonlinear problems from the perspective of PID. Considered a single-layer neural network as using a second-order difference equation and a nonlinear
arXiv:2607.16194v1 Announce Type: new Abstract: In modern financial markets, decision-makers increasingly rely on quantitative methods to navigate complex trade-offs among multiple, often conflicting objectives. This paper addresses constrained multi-objective optimization (MOO) with an application to portfolio optimization for minimizing risk and maximizing return. To address existing gaps, we propose a novel reinforcement learning (RL)-guided non-dominated sorting genetic algorithm II (NSGA-II
arXiv:2607.16227v1 Announce Type: new Abstract: LLMs are increasingly deployed in security-critical systems across healthcare, finance, education, and decision support, yet their inability to forget creates serious cybersecurity, privacy, and safety risks. Sensitive personal information, copyrighted material, hazardous domain knowledge, and memorized training data remain encoded across billions of parameters long after deployment, leaving models vulnerable to extraction, jailbreak attacks, membe
