10:36
Show HN: Fynepdf-pdfa – PDF/A conversion without Ghostscript (MIT)
Article URL: https://github.com/fynepdf/fynepdf-pdfa Comments URL: https://news.ycombinator.com/item?id=50435403 Points: 1 # Comments: 0
Today's news
Products & applications / 01Cisco research: Trust, not technology, is now the speed limit on enterprise AISiliconANGLE AI
01 / IN FOCUS
Cisco research: Trust, not technology, is now the speed limit on enterprise AI
SiliconANGLE AIData & engineering / 02Announcing ClickHouse Observability - fully managed observability on ClickHouse CloudClickHouse
02 / IN FOCUS
Announcing ClickHouse Observability - fully managed observability on ClickHouse Cloud
ClickHouseCompute & infrastructure / 03b12229llama.cpp releases
03 / IN FOCUS
b12229
llama.cpp releasesAI NEWS × FOXAIFind your next step
Explore AI tools From the latest news to tools that work for you.
Discover AI tools
Swipe to explore →E
EvoMapAgents & automation
Open DesignDesign & 3D
AI ShortWriting & content
JAXModels & infrastructure
MemoAIMusic & audio
KiroCoding & development
AssemblyAIMusic & audio
Zoom WorkplaceOffice & productivity
Meta AI助手Assistants & search
My Glow Up AILife & personal
EvoMapAgents & automationEvoMap is an infrastructure designed for the reuse of AI agent experiences. It organizes reusable strategies and repair assets with validation records via the GEP protocol, offering market- and quality-based ranking to help different agents discover, evaluate, and inherit existing capabilities.
分类推荐榜首OOpen DesignDesign & 3DOpenDesign is an open-source design workspace that can connect to local programming agents, use built-in model keys, or leverage cloud-based models, enabling the creation and editing of prototypes, web pages, presentations, and graphics within a design system; local software is free, while model services incur fees.
分类推荐榜首AAI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首JJAXModels & infrastructureJAX is a Python numerical computing library designed for accelerators, specifically tailored for high-performance array computations and large-scale machine learning. It efficiently executes the same code across multiple hardware backends, including CPUs, GPUs, and TPUs.
分类推荐榜首MMemoAIMusic & audioMemoAI is an AI-powered audio-to-text tool that supports localized processing, eliminating the need to upload data and ensuring privacy and security. It can efficiently transcribe YouTube videos, podcasts, and local audio/video files (such as MP4, MP3, AAC, M4A, etc.) into text, while offering core features like multilingual translation, speaker diarization, real-time subtitles, and floating notes—making it ideal for meeting minutes, interview transcription, content learning, and more.
分类推荐榜首KKiroCoding & developmentKiro is an AI engineering tool for developers that organizes requirements into specifications, architectures, and tasks, generates code via agents, and supports the entire workflow—from planning to code review—through property-based testing, execution memory, and integration with development tools.
分类推荐榜首AAssemblyAI is a speech AI platform for developers, offering pre-recorded, real-time, and short-form synchronous transcription APIs. It enables the building of voice-based applications by integrating capabilities such as speaker identification, emotion analysis, chapter and summary extraction, as well as speech agent functionality, dictation, and sensitive information processing.
待评分 · 分类列表推荐ZZoom Workplace is Zoom’s team collaboration platform, integrating video conferencing, chat, calendars, and documents, and leveraging built-in AI to organize discussions, draft messages, and track follow-up tasks.
待评分 · 分类列表推荐MMeta AI助手Assistants & searchMeta's free AI chat assistant
待评分 · 分类列表推荐MMy Glow Up AILife & personalMy Glow Up AI provides free analysis based on selfies, without requiring registration, and can generate hairstyle recommendations and beauty plans that suit you.
待评分 · 分类列表推荐AI, as it happens
1572 published stories1572 storiesClear filters ×
2026-11-10
Follow the timeline10:04
Show HN: Blabla Meter – Jev scores how useful page content is before you read it
Hello thereI built a little Chrome extension that analyzes the content elements on a page, scores their "usefulness" and labels them based on that score. What counts as useful can be customized to your preferences and interests, and it learns from your feedback on the scores.Each element gets a badge with its score; hover it for more details.I'm using Jev, so the basic analysis is very fast and very cheap. You need to add your Jev key and run the small local bridge (it's in the repo).For deeper analysis (e.g. a pareto summary) you bring your preferred AI key.Chrome Web Store: https://chromewebstore.google.com/detail/emjbfdcigbfojhdipap... Comments URL: https://news.ycombinator.com/item?id=50435166 Points: 1 # Comments: 1
08:24
Show HN: I abandoned my AVX2 128-bit fixed-point library
Article URL: https://github.com/arjavsharma91/v4q128 Comments URL: https://news.ycombinator.com/item?id=50434431 Points: 1 # Comments: 1
05:00
Vercel Sandbox snapshot creation is now up to 10x faster
Vercel Sandbox has improved snapshot creation speed by up to 10x, with median time dropping to under 0.4 seconds from 4.4 seconds, and restore speed improving by 50% to 250ms at p50. The enhancements leverage the Vercel Hive Snapshot (VHS) format with more efficient data indexing, enabling parallel read and write operations and faster restoration of both base images and user data. Persistent sandboxes now automatically snapshot upon session end and resume from the latest snapshot by default, using the new format for all new snapshots while existing ones retain the previous format.
04:13
Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base
Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream, alongside agentic retrieval. This post explains how the maxAgentIteration parameter matches retrieval effort to each request, using an illustrative internal banking policy assistant.
03:30
Show HN: Desk - Open-source macOS workspace for CLI coding agents
Article URL: https://github.com/s-nish/desk Comments URL: https://news.ycombinator.com/item?id=50430522 Points: 1 # Comments: 0
03:04
Show HN: Attentry – a local checker that reviews each edit Claude Code makes
Article URL: https://github.com/Aarv-1o/Attentry Comments URL: https://news.ycombinator.com/item?id=50430050 Points: 2 # Comments: 0
01:57
Show HN: Face analysis tools with on-device photo processing
Article URL: https://faceanalysis.app/ Comments URL: https://news.ycombinator.com/item?id=50429010 Points: 1 # Comments: 0
01:31
Show HN: We Gave AI Coding Agents Production Memory
Hi HN, I’m building Codela to help coding agents learn from what happens after their code ships.I realized that my AI agent writes a change, the tests pass, and it gets deployed. Then in production a problem happens, I fix it, but what it did wrong and why never reaches the agent, so futures session usually make the same mistake.Codela checks every deploy against how your app actually behaves in production, learns from the ones that broke it, and teaches your agents so they don’t repeat the mistake.Would love any feedback on this, thanks! Comments URL: https://news.ycombinator.com/item?id=50428670 Points: 1 # Comments: 0
01:00
The observability UI as we know it is dead. So what comes next?
Your observability UI shouldn't limit the questions you can ask. Explore how ClickHouse Observability Apps turns a prompt into custom investigation experiences, why SQL makes it possible, and what we still need to get right.
00:41
What Frontier Labs Buy: A Data Deep Dive with Handshake AI — Garrett Lord & Team
Our first deep dive with an AI data company. In roughly a year, Handshake built an AI training business doing nearly $1 billion in gross annualized revenue. What are frontier labs buying? Garrett Lord joins us with the people building reinforcement lea...
00:23
What Is Eval-Driven Development? How to Improve AI Agents
Eval-driven development helps you build AI agents against a consistent set of metrics. Define good behavior, write the eval first, then compare experiments.
2026-11-09
Follow the timeline20:00
b12220
The Metal kernel for ggml_tri has been updated to use a select operation instead of scaling by comparison, aligning its behavior with the CPU kernel. This change ensures that values outside the triangle are set to zero rather than becoming NaN when encountering ±inf. A new test, test_tri_special, validates this fix across all four triangle types, confirming it passes with the update but failed previously.
13:00
Adaptive Depth Aggregation in Graph Transformers for Long-Range Graph Reasoning
arXiv:2611.08500v1 Announce Type: new Abstract: Graph Transformers improve long-range node-to-node communication through global or structure-aware interactions. However, improving cross-node communication does not determine how computations produced at different depths should be combined. Standard residual streams accumulate successive computations with fixed unit coefficients shared across nodes. This fixed aggregation is a residual-interface constraint: once intermediate contributions have been produced, the interface cannot explicitly reweight them by node. We hypothesize that this constraint can create a depth-wise aggregation mismatch when the relative utility of these intermediate contributions varies across nodes and structural contexts. To study this hypothesis, we formalize Graph Transformer residual computation as a causal node-wise history of graph-propagation and feed-forward network (FFN) contributions, making depth aggregation an explicit interface choice. We realize node-adaptive aggregation over this history with Attention Residuals (AttnRes) while preserving the backbone's graph-propagation and auxiliary-state machinery. Block AttnRes reduces the routing cost of long histories relative to Full AttnRes by pooling consecutive contributions. We instantiate the interface in GPS and GRIT and evaluate it on all five ECHO tasks. Both variants achieve lower mean absolute error (MAE) than their independently tuned backbones on every task, and at least one obtains the lowest mean among all compared methods in each task. Routing-only donor-swap interventions support the mismatch hypothesis, while additional ablations examine the key design choices. Together, these results support node-adaptive depth aggregation as a useful complement to cross-node communication in long-range graph reasoning.
13:00
Adaptive Scheduling Pipeline for Multi-Instance Asynchronous Reinforcement Learning
arXiv:2611.08864v1 Announce Type: new Abstract: We present the Adaptive Scheduling Pipeline (ASP), an offline rollout scheduler for multi-instance asynchronous reinforcement learning (RL) of large language models (LLMs). ASP jointly reduces three sources of rollout underutilization - padding bubbles from intra-minibatch length heterogeneity, skewness bubbles from long-tail outputs, and sorting bubbles from fluctuations in training-queue occupancy induced by length-sorted dispatch - through a single offline preprocessing pass. This enables efficient multi-instance rollout that overcomes the early scaling plateau of single-instance inference while smoothing the arrival of generated samples at the trainer. We integrate the scheduler into an asynchronous architecture that decouples rollout from training while keeping policy lag observable and bounded. Complete ASP improves end-to-end throughput by up to 3.22 times and reduces iteration time by up to 76.8% relative to MindSpeed-RL, while reducing iteration time by up to 62.5% relative to verl. Within ASP, scheduling reduces mean iteration time by 10.9%. ASP also scales more robustly with additional generation resources than these baselines and shows no visible convergence degradation in the measured bounded-lag regime. ASP has since been used in an internal telecom-domain RL post-training workflow, reducing the reported training period from more than three months to about two months and producing a domain-enhanced model for knowledge answering and tool calling.
13:00
Aligning, Fast and Slow: A Control-Theoretic Oversight Framework for Long-Horizon Trajectories and Maintained Deployments
arXiv:2611.08781v1 Announce Type: new Abstract: AI agents can pass checks on individual tasks while retaining memory or code changes that alter their later behavior. We introduce a control-theoretic framework that couples a fast loop controlling proposed actions with a slow loop reviewing persistent changes and reassessing configurations after model or tool updates. When measurement errors and changes between checks are bounded and controllers can enforce their decisions, we derive a deployment-level bound and a rule for dividing review effort. In simulation, dividing a fixed review budget between both loops reduces mean maximum departure from intended behavior roughly twelvefold compared with review confined to individual runs. In coding stress tests with authored memories and five matched seeds, combined controls reduce mean severity on a 0-3 scale from 0.325 without gates to 0.117, resolving 33 of 120 issues versus 35 without gates; in trading stress tests, combined controls reduce mean shortfall in low-emission purchases from 0.892 without gates to 0.107. The overall framework helps developers and auditors compare and enforce oversight designs, while the agent studies test component controls rather than the full deployment-level guarantee.
13:00
An Anatomy-guided 3D Segmentation Pipeline for Prostate Surgical Phantoms from CT Scans
arXiv:2611.08652v1 Announce Type: new Abstract: Full autonomy has been a long-term goal in robotic surgery and a near-to-medium-term goal for prostatectomy. Due to the relatively closed structure of the procedure, its standard-of-care robotic/laparoscopic solutions, and procedure economics, prostate procedures are an optimal early target for surgical automation. Prototyping and testing of possible solutions is done in constructed laboratory phantoms, either synthetic tissues or animal phantoms. To enable measurement of perceptual and robotic motion error, phantoms undergo volumetric imaging; these images are critical to both a potential deployed automatic system, used in planning motion and treatment (cutting, ablation, suturing, etc.), as well as post-hoc assessment of system performance. Rapid iteration on these phantom models yields small, inconsistent datasets, while the current workflow for human annotation is often anatomically unreliable and prohibitively time-consuming, rendering deep learning unsuitable at reasonable scales. To address these limitations, we present an automated 3D segmentation pipeline that uses classical medical image-processing techniques to encode the known anatomy of the phantoms as explicit geometric and intensity priors, which requires no training corpus and is transferred to each new phantom revision without re-annotation. Across 57 scans spanning multiple phantom revisions, our pipeline recovers the capsule interior at 0.83 median Dice on 11 contrast-suppressed scans and detects all 32 annotated focal lesions without false positives, completing a full scan in 2-8 minutes on commodity CPU hardware versus 1-2 hours by hand.
13:00
Aspect-wise Pairwise Tournaments for Test-Time Selection
arXiv:2611.08640v1 Announce Type: new Abstract: Scaling test-time compute has proven highly effective at improving LLM reasoning. A popular method is best-of-n sampling, where a model generates many candidate solutions and one is selected. This motivates the question: how can we select the best candidate? When humans make choices, we find it more natural to compare two options than judge each in isolation. Additionally, when the options become complex, we like to judge the options one aspect at a time, such as comparing two job candidates on experience, communication, etc. In the test-time setting, candidate solutions should be judged in the same way. Here we introduce Aspect-wise Pairwise Tournaments (APT), which verifies by comparison and compares by aspect. Each matchup of a single elimination tournament is decided by a vote over multiple off-the-shelf aspect verifiers, each expressing a pairwise preference along its own aspect. Across five domains and three generator LLMs, APT improves over binary multi-aspect approval, self-consistency and reward model verification, with the largest gains on open-ended tasks. We find that both components matter; neither binary approval over the same aspects nor a generic pairwise judge at a matched budget matches APT. Because aspects are specified in natural language, APT also lets users steer selection toward properties they care about, better aligning with user preferences without needing to regenerate solutions. No component is trained, so APT transfers to new domains by simply rewriting prompts.
13:00
AtariBench: Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay
arXiv:2611.08755v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved strong performance on static visual understanding benchmarks, yet their ability to act in dynamic environments remains less well understood. We introduce AtariBench, a controlled benchmark that evaluates VLMs across 20 Atari 2600 games, requiring models to make sequential decisions from high-temporal-resolution gameplay streams. By decoupling fast in-game dynamics from wall-clock inference speed, AtariBench focuses on whether models can perceive rapid visual state changes, reason over spatiotemporal dynamics, and ground actions in the current observation. Our experiments reveal substantial limitations in state-of-the-art VLMs: models often fail to infer object motion and direction, exhibit brittle sequential decision-making, and over-rely on textual interaction history despite newly appended visual feedback. We further introduce a separability analysis to identify which in-game scores provide reliable signals of model competence, and use the benchmark to study how memory design and prompting strategies affect performance. Overall, AtariBench exposes a persistent gap between passive visual perception and active decision-making, providing a lightweight and rigorous testbed for developing VLMs that can reason and act in dynamic environments.
13:00
AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
arXiv:2611.08752v1 Announce Type: new Abstract: Large language models have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to jailbreak attacks that circumvent safety mechanisms and elicit harmful or unintended outputs. Although safety can be improved through model fine-tuning, such approaches can be computationally expensive and may degrade previously acquired capabilities through catastrophic forgetting. Recent jailbreak defenses have therefore explored targeted interventions on specific model components associated with unsafe behavior. However, existing approaches typically decouple two inherently related decisions: where to intervene and how to modify the selected components. Such sequential optimization may be suboptimal because the optimal intervention location can depend on the intervention applied there, and vice versa. In this work, we introduce AttentionSwitch, the first jailbreak defense to jointly optimize intervention sites and strengths within a frozen LLM. Specifically, AttentionSwitch learns a sparse set of attention heads together with query-conditioned multiplicative scaling factors, allowing the outputs of the selected heads to be either attenuated or amplified without altering the directions of their representations. Across popular language models and jailbreak attacks, AttentionSwitch outperforms existing defenses, with particularly strong results when training data is scarce.
Every update links back to its source.