AI News Today

arXiv:2511.06667v2 Announce Type: replace-cross Abstract: With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies. In contrast, soft robotic simulation frameworks remain scarce and are seldom adopted by the soft robotics community. This gap stems partly from the lack of easy-to-use, general-purpose frameworks and partly from the high computational cost of accurately simulating continuum mechanics, which often

arXiv:2512.05693v2 Announce Type: replace-cross Abstract: Generalist vision--language--action (VLA) policies are typically trained on heterogeneous mixtures of robot demonstrations spanning diverse embodiments, action spaces, and observation configurations. Modeling such heterogeneity with a shared dense action module can induce negative transfer, particularly when action spaces or visual observations differ across data sources. We address this issue with HiMoE-VLA, a VLA framework built around

arXiv:2601.06425v2 Announce Type: replace-cross Abstract: Leakage power in multicore embedded systems now rivals dynamic power, so DVFS schedulers must respect deadlines and thermal limits, not just average makespan. Existing heuristics lack per-core, temperature-aware control and overlook the irregular execution of OpenMP DAGs. We propose HiDVFS, a general, extensible hierarchical multi-agent DVFS scheduler: a profiler agent selects cores and frequencies, a thermal agent groups cores by tempera

arXiv:2603.23800v2 Announce Type: replace-cross Abstract: We present a novel LLM-informed model-based planning framework, and a novel prompt selection method, for object search in partially-known environments. Our approach uses an LLM to estimate statistics about the likelihood of finding the target object when searching various locations throughout the scene that, combined with travel costs extracted from the environment map, are used to instantiate a model, thus using the LLM to inform plannin

arXiv:2604.11840v3 Announce Type: replace-cross Abstract: Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises. In that role a model should reproduce how people plausibly behave, hesitating, conceding late, and settling for imperfect deals, rather than playing the best move. We call this the sampler role, in contrast to the solver role of finding the best move, and we test how the reasoning modes providers ship to strengthen

arXiv:2605.04724v2 Announce Type: replace-cross Abstract: The pervasive integration of AI has enabled Offensive AI: the exploitation of AI for malicious ends across the cyber-kill chain. A critical manifestation is the user attribute inference attack, where AI infers sensitive Personally Identifiable Information (PII) from innocuous public data. We explore how music streaming ecosystems, where users routinely release public playlists, can be exploited for Offensive AI. To quantify this threat, w

arXiv:2605.08332v2 Announce Type: replace-cross Abstract: Feedback-based adaptive quantum optimization (FALQON) is a promising approach for solving combinatorial problems on noisy intermediate-scale quantum (NISQ) devices, requiring only single circuit evaluations per layer. However, standard FALQON relies on fixed hyperparameters that severely limit convergence speed, requiring hundreds to thousands of layers for acceptable solutions. This paper proposes Optimal FALQON, an optimization-based fo

arXiv:2605.11325v3 Announce Type: replace-cross Abstract: Current LLM memory benchmarks evaluate answer quality rather than retrieval accuracy. Consequently, a system that dumps its entire belief store can achieve perfect recall and mask severe precision failures. We show this evaluation gap persists across multiple embedding models where similarity-based retrieval over domain-specific corpora inherently struggles to isolate target beliefs from semantically proximate ones. Furthermore, multi-tur

arXiv:2605.22774v4 Announce Type: replace-cross Abstract: Assessing cognitive load continuously and at low latency would help adaptive human-computer interaction, but it remains hard because labeled data are scarce and models generalize poorly across subjects. Recent ECG foundation models, pre-trained on millions of clinical diagnostic ECG recordings, yet they do not apply directly to wearable devices when the sensor configuration and the task both differ. We present CogAdapt, a framework that a

arXiv:2605.27395v2 Announce Type: replace-cross Abstract: As the rapid proliferation of AI systems and harms spurs efforts in AI governance around the world, prioritizing among competing policy options has become increasingly challenging for policymakers and researchers. We introduce a methodology for identifying viable policy options to mitigate specified AI harms, helping policymakers and researchers target areas that warrant greater time and resource investment. This method combines participa

arXiv:2606.03800v2 Announce Type: replace-cross Abstract: The supply of high-quality training tasks is a central bottleneck for reinforcement learning from verifiable rewards (RLVR) on agentic language models. Each task requires a sandboxed setup, a prompt, and a hand-authored reward function, and only tasks that pass a quality bar produce useful training signal. Hand-curation at this quality bar does not scale economically to the task counts effective RL training requires, and the substitution

arXiv:2606.05403v2 Announce Type: replace-cross Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions. Whether they evaluate the quality of that evidence, or merely aggregate it based on surface presentation, remains poorly understood. We show that models possess the capability to detect fabricated statistics in isolation but do not recruit this capability during multi-source synthesis, producing similar numeric estimates

arXiv:2606.06133v3 Announce Type: replace-cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fin

arXiv:2606.07094v2 Announce Type: replace-cross Abstract: Scientific workflows increasingly generate structured JSON data that is easy to exchange but difficult to interpret consistently across systems due to lacking semantic interoperability. While JSON Schema ensures structural validation, it provides no native support for Linked Data semantics. This paper presents an RDF Authoring View extending the open-source JSON Schema editor MetaConfigurator, enabling researchers to transform existing JS

arXiv:2606.12629v3 Announce Type: replace-cross Abstract: The standard basis of transformer hidden states is a training-free, architecture-general feature basis for detecting concepts and, in language models, steering them; with no learned dictionary. Individual dimensions act as binary registers read one at a time: their signs (+/-1) encode content, their magnitudes strength. A feature is just a subset of dimensions with a consistent sign pattern, read by counting sign agreements. We validate t

arXiv:2606.18664v3 Announce Type: replace-cross Abstract: Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments. Classical methods such as Multiple Signal Classification (MUSIC) offer strong theoretical foundations but degrade under low signal-to-noise ratios. While deep learning-based approaches achieve promising performance, they often struggle with limited generalization across c

arXiv:2606.19042v2 Announce Type: replace-cross Abstract: In vibe coding, an emerging AI-driven paradigm, an LLM generates an entire program from a natural language prompt, but what happens to the variability that traditional software engineering carefully builds into code? To answer this question, we conducted an exploratory analysis on 10 vibe coded C/C++ projects, which suggests that there is near zero in-artifact variability, i.e., at compile- and runtime. All variability decisions are resol

Article URL: https://www.nature.com/articles/d41586-026-02105-3 Comments URL: https://news.ycombinator.com/item?id=48840804 Points: 2 # Comments: 0

Article URL: https://www.forbes.com/sites/annaesakismith/2026/06/23/china-cuts-12200-university-programs-replaces-many-with-ai-degrees/ Comments URL: https://news.ycombinator.com/item?id=48840689 Points: 4 # Comments: 0

Hey, so i'm primarily looking to test out app concepts, seeing how the ui design could look at front-end. Play around with features and ux type of mechanisms. What's exactly the main differences or similarities or pros\cons with each of these 2 options 'just 'having fun' 'testing code' 'using the app locally by myself without shipping it' Comments URL: https://news.ycombinator.com/item?id=48840681 Points: 2 # Comments: 2

<p> Full-duplex voice for ChatGPT </p> <p> <a href="https://www.producthunt.com/products/openai?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/1191675?app_id=339">Link</a> </p>

For the past 3 weeks, I've been hacking on a personal AI that you can text. It's curious about you & proactively figures out ways to help you, while still feeling like a friend. Its personality & proactivity is probably what I've spent the most time working on for this project, testing out a bunch of different models and prompts etc. It has more work to be done for sure, but I kinda like how it's come to be so far! It has its own 24/7 computer and browser (still working on improving its use of t

Article URL: https://yeokhengmeng.com/2025/04/llama2-llm-on-dos/ Comments URL: https://news.ycombinator.com/item?id=48840660 Points: 1 # Comments: 0

Article URL: https://newsletter.deenamousa.com/p/ai-could-keep-poor-countries-poor Comments URL: https://news.ycombinator.com/item?id=48840572 Points: 3 # Comments: 1

Article URL: https://chatbrat.ai/bratlog/best-character-ai-alternatives-2026 Comments URL: https://news.ycombinator.com/item?id=48840543 Points: 2 # Comments: 0

Article URL: https://www.404media.co/meta-patents-ai-device-that-tracks-your-emotions-watches-you-take-your-meds/ Comments URL: https://news.ycombinator.com/item?id=48840514 Points: 7 # Comments: 0

When you're deep in a dense book, do you ever wish you could just ask the author something? If each author had an official AI version of themselves, one they licensed and approved, trained on their books, talks, and interviews, with revenue going back to them and you could pay $15 per book to talk it through in a voice or video call while you read, would you try it? I'm considering building this and want your opinion. Just asking if this interests people, like would you pay for that or at least

Hey guys! With an increase in AI-generated content (a.k.a "Slop"), I made a Chrome extension to help people identify it online. It's sort of a like a rating system on how "slop"-y a page is, and you get to see other people's ratings to determine if the content is AI or not. Go ahead and check it out on the Chrome Web Store, and let me know what you think! Comments URL: https://news.ycombinator.com/item?id=48840353 Points: 3 # Comments: 0

Article URL: https://www.currentai.org/blogs/introducing-the-gap-map-v0-1 Comments URL: https://news.ycombinator.com/item?id=48840224 Points: 1 # Comments: 0

Reading a paper means opening a PDF, then hunting separately for the code, the citations, whether it replicated, and what genes/drugs it touches. I spent a few months trying to fix that. Two parts: 1. The map: I embedded 8.5M papers (arXiv, PubMed Central, bioRxiv, medRxiv), ran UMAP to lay them out in 2D, and render them with a WebGL scatterplot. Every dot is a paper — click it for an LLM TLDR, key findings, citations, peer reviews (where they exist), and similar work. Zoom in and the clusters

Article URL: https://github.com/atelier-ws/atelier Comments URL: https://news.ycombinator.com/item?id=48840196 Points: 2 # Comments: 1

this repo does the indexing parsing and retriving in a way that is fast and more accurate and its not uses Ai to compute https://github.com/RajX-dev/N3MO Comments URL: https://news.ycombinator.com/item?id=48840139 Points: 3 # Comments: 0

Article URL: https://github.com/RightNow-AI/auto Comments URL: https://news.ycombinator.com/item?id=48840103 Points: 1 # Comments: 0

Article URL: https://karlbode.com/the-ai-hype-reckoning-is-upon-us/ Comments URL: https://news.ycombinator.com/item?id=48840092 Points: 2 # Comments: 1

Article URL: https://www.nature.com/articles/d41586-026-02143-x Comments URL: https://news.ycombinator.com/item?id=48840035 Points: 3 # Comments: 1

Article URL: https://www.alecscollon.com/blog/llm-burnout/ Comments URL: https://news.ycombinator.com/item?id=48839984 Points: 57 # Comments: 34

<p> The first goal-driven, proactive AI team for e-commerce </p> <p> <a href="https://www.producthunt.com/products/clawteams?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/1191609?app_id=339">Link</a> </p>

Article URL: https://grandpacad.com/en/blog/public-benchmarks-misled-me-opus-4-7 Comments URL: https://news.ycombinator.com/item?id=48839720 Points: 1 # Comments: 0

It's about what you know, not who you know. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.

Article URL: https://www.ft.com/video/5a5733ea-f8fa-488f-906d-418584b8bc36 Comments URL: https://news.ycombinator.com/item?id=48839655 Points: 1 # Comments: 0