Article URL: https://www.law.com/therecorder/2026/06/12/worst-example-of-misconduct-appellate-court-affirms-sanctions-against-law-firm-for-erroneous-ai-cites/ Comments URL: https://news.ycombinator.com/item?id=48536671 Points: 2 # Comments: 0
One of the beauties of the tech industry is that anyone can learn how to program. Most languages are open source and a lot of the foundational software that make up the bedrock of the most powerful tools today are also free and open source. It’s telling that agents were primarily trained on effective unix. I think no one can deny that frontier models, especially playing around with Fable, that institutions will be separated by those that are willing to spend and those that can’t afford to. The d
I'm excited to share "take 2" of the Prela query language. After sharing the previous version here, I've received some valuable feedback, the main one being the weird unicode-based syntax throwing people off. Prela now has a more familiar SQL-like syntax while adhering to the algebraic principle, which makes the language compositional and controllable, all the while keeping the core engine under 1k lines of code. The engine has also been rewritten from Julia to Rust, resulting in both simpler co
fix(agents): preserve literal current session resolution (#93138) * fix(agents): resolve "current" session alias locally without gateway round-trip The system prompt tells agents to use sessionKey="current" to refer to their own session. Previously, resolveSessionReference sent the literal string "current" to the gateway sessions.resolve action, which rejected it with INVALID_REQUEST and logged a noisy error line on every tool call. The wrapper fell b
What models and hardware you are using? For what purpose? What were the challenges? Any tricks that helped you in doing this? This might help new users like me setup theirs. Comments URL: https://news.ycombinator.com/item?id=48536531 Points: 2 # Comments: 0
This question came up from a tangential discussion. Some one was asking suggestions about systems architecture. I suggested them to look into RCA (root cause analysis) for some big scale failures. Hard part is to find this kind of data publicly. This prompted the question about the data source for Mythos/Fable training. The security bugs reports, fixes are somewhat of a sensitive private collections. I did check the documentation from Anthropic on this, it only mentions the usage of publicly acc
fix(feishu): pass card_msg_content_type to get full card content (fixes #78289) (#93134) * fix(feishu): pass card_msg_content_type to get full card content When reading Feishu interactive card messages via getMessageFeishu, the API returns a degraded structure (title + 'upgrade client' prompt) unless card_msg_content_type=user_card_content is passed in params. Fixes #78289 * fix(feishu): request full card content for message reads --------- Co-authore
Article URL: https://www.totalnoise.ai/blog/educationandai/ Comments URL: https://news.ycombinator.com/item?id=48536463 Points: 2 # Comments: 1
Article URL: https://www.reuters.com/legal/government/google-targets-ai-powered-phishing-new-york-lawsuit-2026-06-12/ Comments URL: https://news.ycombinator.com/item?id=48536446 Points: 1 # Comments: 0
Orbio announces $21 Million Series A in round led by Dawn Capital.
A coding agent with explicit long-term memory architecture Discussion | Link
The European Commission has unveiled its plans for digital sovereignty. Its proposals betray a disappointing lack of vision Beti Hohler is a Slovenian national who lives in the Netherlands. Like tens of millions of other Europeans, she uses Apple’s app store and has an Amazon account. When she travels for work or leisure, she may want to book a place on Airbnb or Booking, using a credit card issued by Visa or Mastercard, perhaps through PayPal. But when the Trump administration <a
arXiv:2606.14119v1 Announce Type: new Abstract: Fault diagnostics and recovery in smart factories is challenging because critical information is dispersed across manuals of multiple machines which are interconnected through the manufacturing process. Large Language Models (LLMs) can provide a promising approach. In this paper, we propose FactoryLLM, a safe and open-source AI playground designed for evaluating different LLM-based retrieval-augmented generation (RAG) models by analysing documents
arXiv:2606.14176v1 Announce Type: new Abstract: Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because the problem statement, diagram, constraints, and solution should be mutually consistent. Existing methods often trade off controllability and reliability: seed-based rewriting is flexible but weakly verifiable, whereas diagram-first construction improves validity but is less suited to arbitrary user
arXiv:2606.14200v1 Announce Type: new Abstract: Open platforms increasingly route tasks among heterogeneous LLM agents--differing in base model, scaffold, and tool stack--whose competence varies sharply by skill: an agent excellent at one skill may be useless at another. The standard reputation approach summarizes each agent by a single global trust score, but that scalar is the wrong object here, because routing every task to the globally most-trusted agent leaves the value of specialization un
arXiv:2606.14211v1 Announce Type: new Abstract: LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback -- even for questions they correctly answered
arXiv:2606.14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows. Skills rarely remain sufficient after deployment: edge cases, API changes, and deployment constraints become visible only through use, making skill evolution a practical necessity. Existing methods depend on privileged feedback such as held-out validation scores, hidden test outcomes, or environment rewards -- signals often unavailable when a prac
arXiv:2606.14240v1 Announce Type: new Abstract: Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human physical understanding and increasingly critical for Large Language Models (LLMs). However, existing affordance benchmarks largely expose explicit object identities in the evaluation setup, allowing models to rely on memorized object-affordance mappings rather than reasoning over physical propertie
arXiv:2606.14249v1 Announce Type: new Abstract: AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive
arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas,
arXiv:2606.14418v1 Announce Type: new Abstract: We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use object-
arXiv:2606.14470v1 Announce Type: new Abstract: Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited. Every other complex software process (code, infrastructure, data, experiments) is version-controlled; reasoning is not. We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository: every scored thought is a commit, scores are n
arXiv:2606.14476v1 Announce Type: new Abstract: A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to rely on such a tool. We test this directly. We expose a frozen GNN to a ReAct-style LLM agent as an explicit tool and measure, on node classification over a text-attributed graph (ogbn-arxiv, replicated on WikiCS), whether the agent uses the tool or merely obeys it. We f
arXiv:2606.14502v1 Announce Type: new Abstract: Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reasoning, action, memory, and self-improvement. We conceptualize this transition as a shift from Chatbot to Digital Colleague: from conversational answers to persistent work. We organize this transition along two tightly coupled dimensions. First, at the cognitive core level, LLMs are advancing from Chatbot-
arXiv:2606.14507v1 Announce Type: new Abstract: Fine-tuning vision-language models to emit dense coordinate lists improves visual grounding but also changes how models serialize, repeat, and terminate structured outputs. We study this behavior as a generation and control surface. In Gemma 4 12B, high-capacity q/k/v/o LoRA raises class-aware F1@0.3 from 0.007 to 0.448 while inducing repeated-tail pressure (duplicate rate 0.080, max repeat 23). A q/v rank sweep keeps max repeat at 21-22 across ran
arXiv:2606.14516v1 Announce Type: new Abstract: AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluat
arXiv:2606.14571v1 Announce Type: new Abstract: A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent observes and how the user interacts with the agent, and the agent must carry them forward from the current request to similar future tasks. Existing memory benchmarks usually test dialogue recall or task improvement in isolation, leaving the trajectory from streaming observa
arXiv:2606.14579v1 Announce Type: new Abstract: When applying Group Relative Policy Optimization (GRPO) for GUI Grounding, rollouts are sampled from a single screenshot view; groups often become either all failures on difficult instances or all successes on easy ones, yielding no useful relative advantage. We propose VISTA (View-Consistent Self-Verified Training), a GRPO-based training framework that constructs each comparison group from multiple target-preserving views of the same GUI instance.
arXiv:2606.14654v1 Announce Type: new Abstract: Sequential or time-stamped interaction logs provide objective records of digital application usage, yet their granularity and noise often obscure meaningful insights into people's work. Such insights are essential for improving digital products in ways grounded in real-world user interactions. Prior research has applied deep learning models to cluster user actions into high-level activities, but these approaches are highly sensitive to noise and st
arXiv:2606.14672v1 Announce Type: new Abstract: Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by concatenating their textual outputs, which discards the
arXiv:2605.13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end of an episode, making it difficult to determine which intermediate actions contributed to success or failure. As a result, propagating delayed outcomes back to individual decision steps without relying on cost
arXiv:2606.13589v1 Announce Type: cross Abstract: We present Simplex-Constrained Sparse Bagging (SCSB), a mathematically rigorous framework for post-training compression and probability calibration of bootstrap-based bagging ensembles. Standard bagging ensembles (such as Random Forests, Bagged SVMs, and Bagged Neural Networks) assign uniform voting power to all constituent estimators. However, this naive uniform prior ignores the varying local competence of base estimators and contributes to mod
arXiv:2606.14129v1 Announce Type: new Abstract: Reconstruction-based anomaly detection is attractive for industrial inspection, but scaling it from category-specific training to a one-for-all setting is challenging. A single model must reconstruct diverse normal appearances without copying abnormal details, which exposes two coupled failure modes: identical shortcut, where anomalies pass through the reconstruction path, and mis-reconstruction, where normal categories are confused with one anothe
arXiv:2606.14162v1 Announce Type: new Abstract: Large-scale video diffusion models often fail to preserve 3D structure over time, causing geometric drift and implausible motion under viewpoint changes. Existing methods usually enforce geometric consistency by using explicit geometry reconstructions, such as depth maps, point clouds, or reconstructed 3D structures, to define conditions, supervision, or reward signals, making the generator sensitive to errors from upstream geometry pipelines. We p
arXiv:2606.14168v1 Announce Type: new Abstract: Text-driven 3D scene generation is a promising technique for digital content creation, embodied AI simulation, and interactive design, yet practical workflows often require refining, extending, or correcting existing scenes while preserving non-target content. Existing methods can produce realistic and structurally plausible scenes, but they generally lack editability with requirement-level state tracking, so part-level failures often lead to full-
arXiv:2606.14194v1 Announce Type: new Abstract: This paper presents a two-stage Hybrid Classical-Quantum (HCQ) pipeline for binary Alzheimer's disease (AD) classification from 3D T1-weighted structural MRI volumes, where the classical and quantum components are designed to complement each other rather than operate independently. A supervised 3D $\beta$-variational autoencoder (VAE) is trained end-to-end under voxel-wise reconstruction, KL-divergence, and focal classification losses that compress
arXiv:2606.14230v1 Announce Type: new Abstract: Deepfakes are artificially generated images, audio, or videos that threaten privacy, security, and information integrity. Detecting such content is crucial for countering disinformation, as the latest models generate highly realistic content. While spatial- or frequency-based approaches achieve good detection rates on Generative Adversarial Networks (GANs)-based generated deepfakes, they often struggle with recent diffusion model-generated images.
arXiv:2606.14251v1 Announce Type: new Abstract: Spatial transcriptomics (ST) links gene expression with tissue morphology but remains expensive and low-throughput, motivating surrogates that infer expression from routine histology. Whole-slide H&E-to-ST inference pairs a gigapixel image with gene measurements at a sparse, irregular set of locations, making multiscale modeling challenging without incurring dense-grid overhead or quadratic token mixing. We propose HiST, a hierarchical sparse trans
arXiv:2606.14292v1 Announce Type: new Abstract: Despite significant advancements in point cloud analysis, reducing energy consumption and improving robustness remain understudied, largely due to the inherent limitations of Convolutional Neural Networks (CNNs). To address this issue, we draw inspiration from the primary visual cortex and propose a Dendritic-Connected Continuous-Coupled Neural Network (DC-CCNN), a novel Brain-Inspired Neural Network (BINN) architecture for point cloud analysis. By
arXiv:2606.14307v1 Announce Type: new Abstract: Recent advances in 3D feedforward reconstruction neural networks have achieved remarkable success in dense reconstruction from images without any camera parameters. Yet, equipping these models with robust semantic understanding remains an open problem. Here we introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework. We build on existing 3D reconstruction models and augment them with a set-based mask
