Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

How Duco transforms financial data automation with Amazon Bedrock AgentCore

Duco, a data automation platform for tier-one banks, rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore. With strict per-tenant isolation, a multi-model strategy, and an MCP skills architecture that cut context overhead by 90%, Duco cut reconciliation deployment time 10x and onboarding costs 70%.

Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore

Novo Nordisk's Manufacturing Technology team within the Tablet area team built a process-intelligence assistant on Amazon Bedrock AgentCore, using a GraphRAG architecture that pairs a knowledge graph in Amazon Neptune with hybrid search in Amazon OpenSearch Serverless to turn millions of controlled manufacturing documents into grounded, cited answers.

Agents are users, so your software needs evals

Agents interact with software through a funnel similar to humans: Discovery, Selection, Access, and Success. To measure whether agents complete user tasks correctly, end-to-end (E2E) evaluations are essential. These tests run multiple trials, score outcomes, and help identify failures across steps like searching cafes, checking budgets, and placing orders. Using frameworks like Harbor, teams can define tasks with specific instructions, environments, verifiers, and known-good solutions. Metrics such as success rate, Pass@k, and Pass^k reveal how reliably agents perform, while trace analysis uncovers root causes of failure. The process includes setting a goal based on observability, customer feedback, or roadmap needs; defining measurable metrics; designing task sets covering common and edge cases; running evaluations at scale using tools like Vercel Sandbox and AI Gateway; and analyzing traces to iterate improvements. Automated trace analysis enables scaling, and repeated evaluation supports continuous improvement, regression detection, and product optimization.

An Operationalization of Opaque Serial Depth

arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverbalized serial cognition a model can perform, as a specific instantiation of the notion of opaque serial depth: roughly, the length of the longest path through a model's computation that does not pass through an interpretable bottleneck. Our main contribution is a particular standard for what counts as such a bottleneck. We define natural-language-rooted (NL-rooted) nodes as nodes that were initialized from a pre-training prior to produce human-understandable outputs, whose output space has not been expanded beyond that prior, and whose outputs the model has not been modified to interpret as a different type of data. By construction, the resulting measure, NLS depth, can be adjudicated before training from an architecture, training recipe, and deployment configuration alone, and is insensitive to ordinary post-training such as prompting, distillation, and RL. We find that, across open-weight models, NLS depth correlates strongly with layer count, with some exceptions, and has grown slowly over recent years. It would likely grow slowly under continued scaling of standard transformers, while latent-reasoning architectures such as full-bandwidth transformers could increase it by a large amount. We work through how NLS depth applies to a range of existing and proposed architectures, discuss alternative operationalizations, and give a worked example bounding the depth of Gemma3-1B. We argue that AI developers should track and report the NLS depth of their models as a complement to direct measurements of CoT monitorability.

Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs

arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The small models practitioners actually ship on-device, Phi-3-mini, Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, and Gemma-2-2B-Instruct, typically at 4-bit precision, sit outside this evidence base. We present a reproducible one-GPU audit of four detectors spanning three paradigms: length-normalized token-margin calibration, a lexical n-gram baseline, and two sampling-based consistency methods (semantic entropy and SelfCheckGPT-NLI) on two small open instruction-tuned models (Llama-3.2-3B-Instruct and Qwen2.5-3B-Instruct) loaded at 4-bit NF4 quantization on a single Colab T4 GPU, evaluated on closed-book TriviaQA. Cross-model ranking transfer is poor: Spearman rho is -0.80 and Kendall tau-b is -0.667, meaning the detector ranking actively inverts between the two models, and the cheap lexical baseline is statistically indistinguishable from the sampling-based consistency detectors on both models under bootstrap 95 percent confidence intervals. As a second, methodological contribution, we show that the standard token-overlap-to-multiple-choice correctness labeler for TruthfulQA-Generation produces near-chance AUROC (0.46-0.59) for all four detectors on both models, a labeler failure, not a detector failure, since the same detectors reach 0.69-0.89 AUROC on TriviaQA under the identical pipeline. We release the harness, prompts, and per-item scores and frame the detector choice explicitly as a fairness-of-error-rates allocation problem for practitioners deploying on resource-constrained, on-device hardware.

HarmonyText: Harmonious Scene Text Editing via Reverse-to-Refined Pair Synthesis and Region-Decoupled Frequency Learning

arXiv:2611.17733v1 Announce Type: new Abstract: Natural language-guided, mask-free scene text editing aims to modify text in real-world images using only textual instructions, yet remains challenged by unreliable pseudo-GT supervision, over-smoothed text generation, and the absence of GT-free evaluation. Existing methods often rely on imperfect pseudo-targets with background discrepancies, while standard MSE-based velocity regression tends to suppress high-frequency details, leading to blurred text boundaries and weakened local textures. To address these issues, we propose HarmonyText, a mask-free scene text editing framework with region- and frequency-aware supervision. HarmonyText introduces Region-Decoupling Optimization (RDO), which aligns edited text regions with pseudo-targets while anchoring preserved regions to the source image, and Cascaded High-Frequency Texture Guidance (CHFTG), which applies cascaded wavelet-domain constraints to preserve sharp boundaries and fine-grained textures of textual content. We further propose Reverse-to-Refined Pair Synthesis (RePair) to construct STE25K, a high-quality 25K paired dataset, and introduce a GT-free evaluation protocol with Color Distribution Divergence and a Harmony Assessment Model. Extensive experiments show that HarmonyText outperforms existing methods in text editing accuracy, background fidelity, color consistency, and perceptual harmony.

QCAP-VQA: Question-Conditioned Capped Prior-Mass Supervision for Medical Visual Question Answering

arXiv:2611.17708v1 Announce Type: new Abstract: Medical visual question answering models can answer correctly without attending to the anatomy that the question names. Automatic region priors allow spatial supervision without expert masks, but they are noisy, and it is unclear how strongly they should shape attention and how their effect should be verified. We present QCAP-VQA, which supervises a subset of cross-attention heads with a question-conditioned prior built from ranked segmentation proposals. Its capped prior-mass objective penalizes insufficient attention inside the prior only below a threshold. We evaluate attention against SLAKE structure boxes that play no role in training, separating attention on the named anatomy from how attention shifts between questions about the same image. QCAP-VQA matches the accuracy of a baseline without spatial supervision (84.26% vs. 84.23%), and every evaluated prior-supervised model places more attention on the annotated structures. Over a 64-fold range of regularization strength, the capped objective keeps prior mass between 0.67 and 0.77, whereas a pooled region-mass objective drives it to 0.97 and loses accuracy. The cost lies in question conditioning: as the constraint widens or strengthens, attention shifts agree less with the expert-defined contrast. Across 13 configurations, prior-referenced and expert-referenced evaluation rank the models in largely opposite order (Spearman correlation of -0.87), and the capped models it favors track the prior's own errors. Because clinical use of medical visual question answering requires answers grounded in the queried anatomy, supervision from automatic priors should be judged against independent anatomical references.

Show HN: 1MB Tenstorrent driver with ptx like kernels

The world of AI used to have people training models for solving substantial issues - like beat world's best go players or solving protein folding. Now that the AI got good, perhaps we forgot a bit how to do it. There is still cheap hardware around for tinkerers and people who want to continue good AI legacy. But the hardware may miss software. It is for those people that I started working on zyx long time ago - ML library in hopes of running on any hardware. One example of such hardware is tenstorrent. But the basics must be built first. And so today I'm showing you skamandros. A tiny, self-contained driver and compiler for tenstorrent cards (tested on p100a). PTX like input, mostly abstracted away hardware details (other than tiling), automatic optimizations and operation fusion. Hope you can use this software to write AI models that people can like. Comments URL: https://news.ycombinator.com/item?id=50509698 Points: 1 # Comments: 0

Show HN: a Rust implementation of the Reticulum mesh networking stack

This is a fork of original rust sdk from https://github.com/BeechatNetworkSystemsLtd/Reticulum-rs/ that I extended significantly to make it fully feature compatible with the reference implementation that is built in python. I wanted to expand the rust sdk to give me full toolbox and easy way to do bindings for different languages including for building mobile apps.it covers the full surface: pathfinding and announce propagation, links, requests, resource transfers(bzip2, same wire format), identity ratchets, tunnels, LXMF messaging with propagation sync, serial/KISS/AX.25, RNode (incl. BLE), IPv6 auto-peering and I2P interfaces, Kotlin and Swift bindings so mobile apps can embed the stack directly.CLI tools (rnstatus, rnpath, rnsh, rnx) are ported too.I've done some experiments with it liek creating a LoRa chat firmware for the M5Stack Cardputer and a full node/repeater for M5Stack Unit C6L to have a tiny reticulum node with full stackBefore anyone gives me shit - I've opened an upstream PR but given the size of the change I'dnt blame them for not wanting to deal with it. Comments URL: https://news.ycombinator.com/item?id=50506235 Points: 1 # Comments: 0

Show HN: Paintpot – Kid-friendly MSPaint clone for Linux

Most of the alternatives diverged from the true fun of MSPaint that I had as a child. My children also seem to enjoy this. The closest existing project was "Drawing" on Linux, but I felt it couldn't decide if it was a vector or a raster editor, and this confused my kids, and made good fill pours difficult.Features added beyond original Paint: - Draw circles starting from the center. - OKLCH Palette - Visible pixel grid when zoomed in. - Builds on Linux and Windows. - Written in rust. Comments URL: https://news.ycombinator.com/item?id=50501354 Points: 1 # Comments: 0

b12377

The update refactors DFlash-based speculative decoding methods in llama.cpp by restructuring code organization, sharing components across models, splitting decoder graphs per head, and introducing dedicated classes for DFlash2 and LiliCorr drafts. It also adds support for new draft types, improves documentation, and removes unused code.