AX·NEWS
Sign in

Software Engineering

Software Engineering news — Monday 26 October 2026

109 stories from 5 sources, every one in English. Each links to its publisher.

Open in the live feedRSS feedOn a TV

  1. Oldest GUI application that still runs on Windows 11
    USlobste.rs

    Comments

  2. The EPA Is Quietly Killing Its Web Archive
    USHacker News Front Page

    Article URL: https://www.motherjones.com/environment/2026/10/epa-online-archive-deletion-zeldin-camp-lejeune-trump-clean-power/ Comments URL: https://news.ycombinator.com/item?id=50249275 Points: 150 # Comments: 21

  3. A faster way to compute signed 64-bit floor division by constants
    USlobste.rs

    Comments

  4. US designates helium as a critical material
    USHacker News Front Page

    Article URL: https://apnews.com/article/energy-critical-materials-minerals-helium-43da160adc1bad389fba0b9ffbd14c3c Comments URL: https://news.ycombinator.com/item?id=50248665 Points: 122 # Comments: 63

  5. Type Server Protocol
    USHacker News Front Page

    Article URL: https://github.com/microsoft/pylance-release/blob/main/docs/tsp/type-server-protocol.md Comments URL: https://news.ycombinator.com/item?id=50248371 Points: 138 # Comments: 97

  6. GPT-6.1 Terra
    USHacker News Front Page

    Article URL: https://openai.com/index/introducing-gpt-6-1-terra/ Comments URL: https://news.ycombinator.com/item?id=50248124 Points: 372 # Comments: 225

  7. Meta Employees Denounce Interference in Brazilian Elections
    USHacker News Front Page

    Article URL: https://www.panamericandispatch.org/p/meta-employees-denounce-interference Comments URL: https://news.ycombinator.com/item?id=50248061 Points: 105 # Comments: 13

  8. Oldest GUI application that still runs on Windows 11
    USHacker News Front Page

    Article URL: https://blog.enlyth.com/posts/oldest-windows-gui-app-win-11/ Comments URL: https://news.ycombinator.com/item?id=50248055 Points: 171 # Comments: 91

  9. Less Is More: From 1M Lines of Firmware to 300 of Assembly
    USlobste.rs

    Comments

  10. CSS-Tricks has a new owner
    USlobste.rs

    Comments

  11. In Leaked Audio, Flock CEO Tells Cops Backlash to the Company Isn't Real
    USHacker News Front Page

    Article URL: https://www.404media.co/in-leaked-audio-flock-ceo-tells-cops-backlash-to-the-company-isnt-real/ Comments URL: https://news.ycombinator.com/item?id=50248005 Points: 176 # Comments: 94

  12. The result of the C++26 DIS ballot
    USlobste.rs

    Comments

  13. Pharo 14 Released
    USlobste.rs

    Comments

  14. ChatGPT Keeps Telling People 404 Media Can Solve Their Tech Support Problems
    USHacker News Front Page

    Article URL: https://www.404media.co/chatgpt-keeps-telling-people-404-media-can-solve-their-tech-support-problems/ Comments URL: https://news.ycombinator.com/item?id=50247630 Points: 175 # Comments: 57

  15. Concerning behavior from a popular open-weight AI model
    USHacker News Front Page

    Article URL: https://cohere.com/blog/concerning-behaviour-popular-open-weight-ai-model Comments URL: https://news.ycombinator.com/item?id=50246658 Points: 205 # Comments: 76

  16. Stalwart v1.0: The Fastest Mail Server on the Planet
    USlobste.rs

    Comments

  17. Web Page Crawler Revealed - Information Camouflage
    USlobste.rs

    The story is a technical breakdown attempting to trace a series of crawlers from Contabo GmbH. Edited the title to be more clear. This feels relevant here but I struggled with tagging this. I welcome suggestions for how to tag it better!…

  18. CSS-Tricks has a new owner
    USHacker News Front Page

    Article URL: https://css-tricks.com/css-tricks-has-a-new-owner/ Comments URL: https://news.ycombinator.com/item?id=50245831 Points: 311 # Comments: 69

  19. Heavenly delights of hashing numbers under EQUALP
    USlobste.rs

    Comments

  20. Microsoft offers mass buyouts for roughly a quarter of its workforce
    USHacker News Front Page

    Article URL: https://www.seattletimes.com/business/microsoft/microsoft-offers-mass-buyouts-for-roughly-a-quarter-of-its-workforce/ Comments URL: https://news.ycombinator.com/item?id=50245524 Points: 389 # Comments: 346

  21. CSS-Tricks has a new owner!
    USCSS-Tricks

    Yes, I've got the keys to the castle, so to speak. And, even after 12 years of working on the site, I'll admit I'm a little overwhelmed and nervous about that. CSS-Tricks has a new owner! originally handwritten and published with love on…

  22. Sebastian Raschka's from-scratch video course on building reasoning models
    USHacker News Front Page

    Article URL: https://magazine.sebastianraschka.com/p/building-reasoning-models Comments URL: https://news.ycombinator.com/item?id=50245138 Points: 468 # Comments: 64

  23. OLED iPad Mini
    USHacker News Front Page

    Article URL: https://www.apple.com/shop/buy-ipad/ipad-mini Comments URL: https://news.ycombinator.com/item?id=50243646 Points: 151 # Comments: 202

  24. Simple Sudoku Solver in Assembly
    USlobste.rs

    Comments

  25. Why is it so expensive to send an email?
    USlobste.rs

    Comments

  26. Shadow: Dummy folders, an obvious overflow, and a ROP chain
    USlobste.rs

    Comments

  27. Aggro is the Foundation (2022)
    USlobste.rs

    Comments

  28. Anthropic S-1
    USHacker News Front Page

    Article URL: https://www.sec.gov/Archives/edgar/data/2130357/000162828026067168/anthropicpbc-sx1.htm Comments URL: https://news.ycombinator.com/item?id=50242939 Points: 1335 # Comments: 1317

  29. Fixing Tool-Call Accuracy in vLLM
    USHacker News Front Page

    Article URL: https://www.ubicloud.com/blog/fixing-tool-call-accuracy-in-vllm Comments URL: https://news.ycombinator.com/item?id=50242870 Points: 138 # Comments: 64

  30. Brown student maps the hidden global labor powering AI
    USHacker News Front Page

    Article URL: https://www.brown.edu/news/2026-10-26/ai-data-workers Comments URL: https://news.ycombinator.com/item?id=50242843 Points: 159 # Comments: 138

  31. From impulse purchase to pocket studio: The M-Vave FM-1
    USlobste.rs

    Comments

  32. Websites Should Be Printable
    USlobste.rs

    Comments

  33. Gram 3.4.0 released
    USlobste.rs

    Comments

  34. What are you doing this week?
    USlobste.rs

    What are you doing this week? Feel free to share! Keep in mind it’s OK to do nothing at all, too.

  35. The Small Web is Huge
    USlobste.rs

    Speaker Page: https://pretalx.seagl.org/2026/talk/GQZEUY/ Additional Notes: https://punkto.org/blog/small_web Comments

  36. Wails v3.0.0 Released
    USlobste.rs

    Comments

  37. Pharo 14
    USHacker News Front Page

    Article URL: https://pharo.org/news/2026-10-26-Pharo14Release.html Comments URL: https://news.ycombinator.com/item?id=50241925 Points: 214 # Comments: 52

  38. Akku.scm 1.2.0 released
    USlobste.rs

    Comments

  39. MoLE Protocols
    USlobste.rs

    This document defines protocols that instantiate the MoLE architecture: two endorsement protocols, by which a Client proves to a Moderator that it holds an Endorsement from a trusted Anchor without revealing which one, and three credential…

  40. Websites Should Be Printable
    USHacker News Front Page

    Article URL: https://brennenputh.me/blog/printable-websites/ Comments URL: https://news.ycombinator.com/item?id=50241664 Points: 224 # Comments: 160

  41. About the compromised eMudhra intermediate CAs
    USlobste.rs

    Comments

  42. Switzerland. Block by block. At 1:1 scale
    USHacker News Front Page

    Article URL: https://blocks.manifold3d.ch/ Comments URL: https://news.ycombinator.com/item?id=50240922 Points: 438 # Comments: 208

  43. OpenLDK: Bringing the Java World into Common Lisp
    USlobste.rs

    Comments

  44. Two's a Crowd: Human and AI-Based Copresence for Developers with ADHD
    USarXiv cs.SE (Software)

    arXiv:2609.21254v3 Announce Type: replace-cross Abstract: Effective collaboration and communication are vital to developer productivity and well-being, yet remain constrained by human factors such as attention, intrinsic motivation, and…

  45. Automated Multi-Line Bug Repair Using Model Checker Aided LLMs: A Case Study on RISC-V Processors
    USarXiv cs.SE (Software)

    arXiv:2610.32597v1 Announce Type: cross Abstract: Functional verification of Register-Transfer Level(RTL) designs has become a critical bottleneck in modern semiconductor development, often consuming the majority of project resources…

  46. Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence
    USarXiv cs.SE (Software)

    arXiv:2610.32876v1 Announce Type: new Abstract: Pipelines that combine large language models (LLMs) with static analysis let the model consume the analyser's output as evidence, but whether the model distinguishes true from false evidence…

  47. Are LLM-Generated Formal Specifications Faithful to Their Requirements? A Study on Bimodal Formal Specification Generation
    USarXiv cs.SE (Software)

    arXiv:2610.32053v1 Announce Type: new Abstract: Formal specification generation is a critical step towards formal verification and correctness assurance of software. Recently, large language models have been widely adopted in automatic…

  48. Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting
    USarXiv cs.SE (Software)

    arXiv:2610.02571v2 Announce Type: replace Abstract: As AI-assisted programming becomes increasingly mainstream, the environmental impact of AI-generated software has emerged as an important consideration. This motivates evaluating…

  49. From Faulty Claims to Incorrect Patches: An Empirical Study of Task-Grounded Reasoning in Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.32338v1 Announce Type: new Abstract: Large language model (LLM)-based coding agents increasingly resolve real-world software engineering tasks, yet still fail on many of them. Prior trajectory studies characterize these failures…

  50. What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md
    USarXiv cs.SE (Software)

    arXiv:2610.31715v1 Announce Type: new Abstract: Coding agents can be guided with instruction files in a repository. We examine this emerging practice through a census of popular, active GitHub repositories in thirteen languages, treating…

  51. Shorter Is Not Cheaper: A Controlled Comparison of Declarative Animation Specifications and Free-Form Code for LLM-Generated Explanations
    USarXiv cs.SE (Software)

    arXiv:2610.32129v1 Announce Type: cross Abstract: Chat assistants increasingly answer conceptual questions with interactive, animated explanations, generated either as free-form HTML/JavaScript or as declarative specifications that a fixed…

  52. When Agents Fail: Model or Harness--Who's to Blame?
    USarXiv cs.SE (Software)

    arXiv:2610.32483v1 Announce Type: cross Abstract: LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated through their…

  53. CuraLoc: Repository-Level Fault Localization via Planned Code Inspection
    USarXiv cs.SE (Software)

    arXiv:2610.31809v1 Announce Type: cross Abstract: A bug report describes what went wrong, but rarely where the code should change. Existing repository-level localization methods often let language models iteratively decide what code to…

  54. Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers
    USarXiv cs.SE (Software)

    arXiv:2610.32110v1 Announce Type: cross Abstract: Agents and verifiers often rely on the text a tool prints, and that text can misrepresent what the tool actually did, even when the tool's computation is correct. We saw this happen in a…

  55. On the Expressive Power of Hook-Indexed State Comprehending State in the React UI Library
    USarXiv cs.PL (Programming)

    arXiv:2610.32925v1 Announce Type: new Abstract: React is currently the most popular JavaScript library for front-end web development. It endows UI components with state via the useState construct, through a mechanism that we name…

  56. Pairing Matters: Performance, Failures, and Efficiency in Lightweight Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.32131v1 Announce Type: new Abstract: Self-hosting coding agents is often necessary for software-engineering teams that must keep proprietary code and development traces within controlled infrastructure. Lightweight, open-weight…

  57. OpenDraco: A Platform for Engineering and Experimenting with Configurable Multi-Agent Architectures for Software Engineering
    USarXiv cs.SE (Software)

    arXiv:2610.32686v1 Announce Type: new Abstract: Experimenting with LLM-based multi-agent systems (MAS) involves an iterative cycle of modeling configurations, executing and evaluating them, comparing results, and refining system designs…

  58. OPTARI: An open-source software framework for clinical translation of optoacoustic imaging
    USarXiv cs.SE (Software)

    arXiv:2610.32468v1 Announce Type: new Abstract: Combined optoacoustic (OptA) and ultrasound imaging is a promising modality across a wide range of pathologies. Its use in clinical research, however, is limited by a lack of analysis…

  59. RubricCraft: Where Solutions Diverge, Criteria Emerge
    USarXiv cs.SE (Software)

    arXiv:2610.31707v1 Announce Type: new Abstract: Evaluating language agents on open-ended, artifact-producing tasks is difficult: model-based graders can be inconsistent, while exhaustive programmatic checks are often impractical. Textual…

  60. WaitLens: Temporal VLM-Based Adaptive Waiting for Industrial GUI Testing Agents
    USarXiv cs.SE (Software)

    arXiv:2610.32482v1 Announce Type: new Abstract: Improving the efficiency of GUI testing agents is important for industrial deployment. Beyond LLM inference, fixed waiting between consecutive interactions introduces substantial overhead…

  61. A Reduced Stochastic Model of Microservice Availability: Algorithms for Identification and Formal Analysis
    USarXiv cs.SE (Software)

    arXiv:2607.00740v2 Announce Type: replace Abstract: Estimating microservice operation availability requires connecting runtime observations to completion of the required work within a deadline. Detailed architectural models provide one…

  62. Loop Engineering: Building Blocks, Adoption, and Impact
    USarXiv cs.SE (Software)

    arXiv:2608.21884v3 Announce Type: replace Abstract: Over the past months, the way developers guide agentic AI coding tools has moved up several levels of abstraction, from phrasing prompts to engineering context to configuring the harness…

  63. Complexity concentration as a god-class and god-method detector: a pre-registered test of a scale-free outlier rule against tool definitions and human labels
    USarXiv cs.SE (Software)

    arXiv:2610.32466v1 Announce Type: new Abstract: God-class and god-method detectors mark concentrated complexity with a raw-scale threshold, a constant fitted on a corpus and re-fitted when the population moves. This paper pre-registers a…

  64. Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows
    USarXiv cs.SE (Software)

    arXiv:2610.31916v1 Announce Type: cross Abstract: A durable agent can resume a consequential action while its authority changes and the action's external outcome remains uncertain. We study execution-time reliability of tool-using AI…

  65. StateMirror: Pre-Execution Detection of Hallucinated Tool Calls in Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.32648v1 Announce Type: new Abstract: Large language model (LLM)-based coding agents may propose invalid actions that are not applicable in the execution environment, such as accessing non-existent paths or missing packages. We…

  66. Beyond Correctness: How Novice Software Engineering Students Exercise Oversight of Generative AI
    USarXiv cs.SE (Software)

    arXiv:2610.32118v1 Announce Type: new Abstract: Generative AI (GenAI) is shifting software engineering students' work from producing artefacts towards evaluating and supervising AI-generated outputs. However, little is known about what…

  67. Beyond Coverage and Mutation: A Blind-Spot Analysis of LLM-Generated Unit Tests
    USarXiv cs.SE (Software)

    arXiv:2610.32548v1 Announce Type: new Abstract: Existing evaluation protocols for unit tests rely on aggregate metrics such as branch coverage and mutation score. These metrics quantify the extent to which a test suite exercises program…

  68. Guard Analysis and Safe Erasure Gradual Typing: a Type System for Elixir
    USarXiv cs.PL (Programming)

    arXiv:2408.14345v5 Announce Type: replace Abstract: We formalize a new type system for Elixir, a dynamically typed functional programming language of growing popularity that runs on the Erlang virtual machine. Our system combines gradual…

  69. Mining the Design Space of Multi-Agent Workflows
    USarXiv cs.SE (Software)

    arXiv:2610.31709v1 Announce Type: new Abstract: Designing large language model (LLM) multi-agent systems (MAS) still relies on trial and error and informal "folk wisdom." Manual studies test only a few communication structures or…

  70. Can AI Agents Help Robotic Engineers? Lessons from Two Focus Days in Industry
    USarXiv cs.SE (Software)

    arXiv:2610.32636v1 Announce Type: new Abstract: Software developers increasingly use AI agents that execute multi-step programming tasks on their own. However, it is unclear if and how this transfers to robotic engineering, where engineers…

  71. On the Expressiveness of Asynchronous Processes with Nested Session Types
    USarXiv cs.PL (Programming)

    arXiv:2610.32558v1 Announce Type: new Abstract: Session types are a type-based approach to correct message-passing programs, where types specify protocols for channels and type checking guarantees communication correctness. Traditional…

  72. Are LLM-Generated Formal Specifications Faithful to Their Requirements? A Study on Bimodal Formal Specification Generation
    USarXiv cs.PL (Programming)

    arXiv:2610.32053v1 Announce Type: cross Abstract: Formal specification generation is a critical step towards formal verification and correctness assurance of software. Recently, large language models have been widely adopted in automatic…

  73. GLP Networking API Specification
    USarXiv cs.PL (Programming)

    arXiv:2610.32583v1 Announce Type: cross Abstract: Multiagent deterministic GLP (madGLP) runs Grassroots Logic Programs (GLP) as agents that communicate solely by asynchronous message passing, and assumes fair delivery: every message sent…

  74. Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant
    USarXiv cs.SE (Software)

    arXiv:2610.31703v1 Announce Type: new Abstract: Most questions that reach an HPC help desk have already been answered in the center's user guides or in a ticket someone else filed last semester; users still file new tickets because the…

  75. MBABench-2.0: Evaluating AI Agents on Constructing Financial Spreadsheets Beyond Simple Verifiability
    USarXiv cs.SE (Software)

    arXiv:2610.31711v1 Announce Type: new Abstract: Spreadsheets are the lingua franca of modern finance, driving valuation, forecast, audit, and many other core workflows of the industry. As LLM agents advance to automate knowledge work…

  76. CrowdStrike Channel File 291: An Engineering Analysis of a Global Endpoint Outage
    USarXiv cs.SE (Software)

    arXiv:2610.32078v1 Announce Type: new Abstract: On July 19, 2024, a CrowdStrike Falcon content update caused Windows systems to crash, affecting about 8.5 million devices according to a Microsoft estimate. The immediate defect was an…

  77. Knowing When to Stop: The Evidence-Action Gap in Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.31895v1 Announce Type: new Abstract: Coding agents are trained to complete tasks, and they keep trying even when the environment makes completion impossible. The evidence that only outside help can restore progress usually…

  78. Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance
    USarXiv cs.SE (Software)

    arXiv:2610.32555v1 Announce Type: new Abstract: LLM agents increasingly rely on external tools exposed via the Model Context Protocol (MCP), yet current benchmarks assume tools respond correctly and on time, leaving agent resilience to…

  79. Lessons Outlive Their Failures: A Case Study of Rules for AI Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.32578v1 Announce Type: new Abstract: AI coding agents increasingly work inside a harness: rule files such as AGENTS.md, on-demand skills, runtime hooks and automated checks. Most studies of harnesses look at a single point in…

  80. Runtime BiDi Structural Verification Catches Right-to-Left Layout Defects that Accessibility, Actionability, and Logical-Property Linting Miss
    USarXiv cs.SE (Software)

    arXiv:2610.32934v1 Announce Type: new Abstract: Bidirectional (right-to-left, RTL) layout defects arise when interfaces authored with physical directional CSS (margin-left, border-left, text-align:left) are rendered under dir="rtl" without…

  81. Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations
    USarXiv cs.SE (Software)

    arXiv:2610.32891v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to optimize code for performance. This practice often assumes that improvements in execution speed naturally translate into overall lower…

  82. daVinci-Env: Open SWE Environment Synthesis at Scale
    USarXiv cs.SE (Software)

    arXiv:2603.13023v3 Announce Type: replace Abstract: Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test…

  83. From Research to Practice: An Interactive Rapid Review of Autonomous Driving System Testing in Industry
    USarXiv cs.SE (Software)

    arXiv:2605.00531v2 Announce Type: replace Abstract: Autonomous driving systems (ADS) are increasingly deployed in real traffic, yet testing remains fundamentally challenging due to open environments, complex scenarios, and the lack of…

  84. SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges
    USarXiv cs.SE (Software)

    arXiv:2610.28886v2 Announce Type: replace-cross Abstract: LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training. Their decisions are useful only when each judge responds reliably to changes…

  85. DeepAVR: Deep Analysis via Multi-Agent Collaboration for Automated Vulnerability Repair
    USarXiv cs.SE (Software)

    arXiv:2610.32345v1 Announce Type: new Abstract: Automated Vulnerability Repair (AVR) has emerged as a critical defense against software security flaws, aiming to triage and fix bugs autonomously. Early LLM-based approaches focused on patch…

  86. Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.31710v1 Announce Type: new Abstract: Context compaction lets long-horizon coding agents continue beyond their context windows, but can erase the state needed to finish a task. Prior evaluations measure efficiency, retained…

  87. Ulysses: A Security Harness For Synthesizing Verifiable Web Exploits
    USarXiv cs.SE (Software)

    arXiv:2610.31831v1 Announce Type: cross Abstract: How can an AI agent automatically discover security vulnerabilities in any software repository? Existing approaches use LLMs to generate software vulnerability exploits. However, it is…

  88. Interaction-as-a-Judge
    USarXiv cs.SE (Software)

    arXiv:2610.17895v3 Announce Type: replace-cross Abstract: Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications…

  89. Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study
    USarXiv cs.SE (Software)

    arXiv:2610.31698v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly complete tasks through live graphical user interfaces (GUIs). Because the model cannot directly operate the GUI, these systems often rely on…

  90. SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software?
    USarXiv cs.SE (Software)

    arXiv:2610.31854v1 Announce Type: new Abstract: Greenfield software development in freelance settings requires coding agents to turn incomplete client requests into working software. This makes requirement clarification essential, yet…

  91. From Regulation to Engineering: Organizational Privacy Climate as Mediator
    USarXiv cs.SE (Software)

    arXiv:2610.32576v1 Announce Type: cross Abstract: Data protection legislation aims to protect privacy rights by regulating how information systems store and process personal information. While such legislation defines legal obligations…

  92. Memoir: Learning, Verifying, and Evolving False-Positive Memories for Static Application Security Testing Tools
    USarXiv cs.SE (Software)

    arXiv:2608.09181v2 Announce Type: replace Abstract: Static Application Security Testing (SAST) tools have become indispensable in modern secure software devel- opment. However, these tools often generate false-positive (FP) alerts…

  93. Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents
    USarXiv cs.SE (Software)

    arXiv:2602.22402v2 Announce Type: replace Abstract: As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codebase conventions -- within the context…

  94. The Influence of Code Smells in Efferent Neighbors on Class Stability
    USarXiv cs.SE (Software)

    arXiv:2602.12950v3 Announce Type: replace Abstract: Understanding what drives code instability is essential for effective software maintenance, as unstable classes require larger or more frequent edits and increase the risk of unintended…

  95. Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems
    USarXiv cs.SE (Software)

    arXiv:2610.31722v1 Announce Type: cross Abstract: Microservice systems have become a dominant architecture for large-scale cloud applications, enabling rapid deployment and elastic scaling. However, ensuring the reliability and…

  96. Large-Scale Study of GitHub Copilot Trajectories
    USarXiv cs.SE (Software)

    arXiv:2610.32313v1 Announce Type: new Abstract: AI coding agents are increasingly integrated into software development workflows. However, most coding agent studies rely on benchmarks similar to SWE-bench, which assume autonomous agents…

  97. Search-Based Testing of Modality Sensitivity in Vision Language Models
    USarXiv cs.SE (Software)

    arXiv:2610.32360v1 Announce Type: cross Abstract: Vision-language models (VLMs) process images and text jointly, yet robustness evaluations often perturb these inputs separately or assess only predefined corruption levels. Such evaluations…

  98. Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control
    USarXiv cs.SE (Software)

    arXiv:2610.31712v1 Announce Type: new Abstract: Mobile GUI agents frequently perform repetitive tasks with similar interaction procedures. Reusing previous executions can reduce redundant LLM inference and execution overhead, but…

  99. CC4Q Workbench: From Quantum Repositories to Analyzable Code Comments
    USarXiv cs.SE (Software)

    arXiv:2610.32651v1 Announce Type: new Abstract: Quantum software development kits (SDKs) expose high-level APIs whose use requires an understanding of underlying mathematical principles, circuit semantics, and hardware properties. Code…

  100. Behind the scenes at the NeXT Computer office
    USHacker News Front Page

    Article URL: https://exhibits.stanford.edu/menuez/browse/next-computer-inc?per_page=96&sort=pub_year_isi+asc%2C+title_sort+asc&view=masonry Comments URL: https://news.ycombinator.com/item?id=50238763 Points: 232 # Comments: 139

  101. PaperPilot – Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP
    USHacker News Front Page

    Article URL: https://github.com/KrushnaVardhanReddy/PaperPilot Comments URL: https://news.ycombinator.com/item?id=50238739 Points: 222 # Comments: 77

  102. Show HN: TitleArt – Make text like it's 1997
    USHacker News Front Page

    Article URL: https://titleart.dvy.io/ Comments URL: https://news.ycombinator.com/item?id=50238708 Points: 376 # Comments: 69

  103. The State of Context Engineering
    USlobste.rs

    This was interesting to me because I was under the naïve impression that context management was a thing of the past, but in actuality it's the opposite: context is here to stay, and managing it has different problems now than it did in the…

  104. writing about pratt parsing so I remember it
    USlobste.rs

    Comments

  105. IBM CEO says open weight models are now good and cheap on-prem
    USHacker News Front Page

    Article URL: https://www.theregister.com/systems/2026/10/22/ibm-ceo-says-open-weight-models-are-now-irresistibly-good-and-cheap-on-prem/5304640 Comments URL: https://news.ycombinator.com/item?id=50238088 Points: 345 # Comments: 248

  106. Removing Next.js Got My Blog to 100 on Every Lighthouse Category
    USHacker News Front Page

    Article URL: https://korindiehacker.bloffy.blog/en/removing-nextjs-got-my-blog-to-100-on-every-lighthouse-category Comments URL: https://news.ycombinator.com/item?id=50237712 Points: 142 # Comments: 79

  107. Lula wins election after final votes tallied
    USHacker News Front Page

    Article URL: https://www.reuters.com/live/brazil-election-live-lula-bolsonaro-face-off-presidential-runoff-2026-10-25/ Comments URL: https://news.ycombinator.com/item?id=50237485 Points: 364 # Comments: 338

  108. “AI Skills” are worthless in 2026
    USlobste.rs

    Comments

  109. Steal My Bitcoin CTF PoC
    USHacker News Front Page

    Article URL: https://github.com/KillaBoi/StealMyBitcoin-PoC Comments URL: https://news.ycombinator.com/item?id=50237379 Points: 141 # Comments: 36