Reading candidates 2026-06-28

[github-actions]

Reading candidates 2026-06-28

These links were collected automatically from curated RSS feeds.
Please review them before adding anything to reading/YYYY/MM.md.

• Window: last 7 days
• Max items: 24
• Max per source: 2

Candidates

1. simonw/browser-compat-db

• Link: https://simonwillison.net/2026/Jun/24/browser-compat-db/#atom-everything
• Source: Simon Willison
• Language: en
• Published: 2026-06-24
• Matched topics: llm, agent, coding-agent
• Score: 9
• Draft summary: simonw/browser-compat-db Inspired by Mozilla's new MDN MCP service - source code here - I decided to try converting their comprehensive mdn/browser-compat-data repository full of browser compatibility data into a SQLite database. This new GitHub repo includes a Claude Code for...

2. Incident Report: CVE-2026-LGTM

• Link: https://simonwillison.net/2026/Jun/26/incident-report/#atom-everything
• Source: Simon Willison
• Language: en
• Published: 2026-06-26
• Matched topics: agent, infra, safety
• Score: 8
• Draft summary: Incident Report: CVE-2026-LGTM Spectacular hypothetical incident report by Andrew Nesbitt. Day 2, 16:00 UTC --- Two AI review agents from competing vendors, both attached to a downstream pull request bumping foxhole-lz4 , enter a disagreement loop over whether the package is m...

3. ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

• Link: https://arxiv.org/abs/2606.27027v1
• Source: arXiv cs.AI
• Language: en
• Published: 2026-06-25
• Matched topics: llm, agent, rag, safety
• Score: 8
• Draft summary: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such...

4. AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing

• Link: https://arxiv.org/abs/2606.26787v1
• Source: arXiv cs.CL
• Language: en
• Published: 2026-06-25
• Matched topics: llm, infra, safety, training
• Score: 8
• Draft summary: Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, poor utilization of unstructured information, and misalignment with long-term business objectives such as cumulative Gross Merchandise Value (GMV), Return on Investment (ROI) and...

5. OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

• Link: https://arxiv.org/abs/2606.27154v1
• Source: arXiv cs.AI
• Language: en
• Published: 2026-06-25
• Matched topics: llm, agent, eval
• Score: 7
• Draft summary: Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, existing datasets suffer from a fundamental gap: they label only the root cause, not the propagation path connecting it...

6. Semantic Early-Stopping for Iterative LLM Agent Loops

• Link: https://arxiv.org/abs/2606.27009v1
• Source: arXiv cs.LG
• Language: en
• Published: 2026-06-25
• Matched topics: llm, agent, rag
• Score: 7
• Draft summary: Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iteration cap (max_iterations). This is a syntactic kill-switch: it is blind to whether the answer is still improving, so it over-s...

7. RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning

• Link: https://arxiv.org/abs/2606.26997v1
• Source: arXiv cs.LG
• Language: en
• Published: 2026-06-25
• Matched topics: llm, infra, training
• Score: 7
• Draft summary: Large language model (LLM) post-training for reasoning increasingly relies on reinforcement learning with verifiable rewards (RLVR), where models learn from ground-truth feedback on mathematical, logical, and scientific tasks. To enable flexible resource allocation and support...

8. Visual Studio Code 1.126 发布

• Link: https://www.oschina.net/news/467075/vs-code-1-126-released
• Source: OSChina AI
• Language: zh-CN
• Published: 2026-06-25
• Matched topics: agent, coding-agent, infra, safety
• Score: 7
• Draft summary: Visual Studio Code 1.126 现已发布 。此版本带来了更清晰的成本透明度、更简单的模型调优以及更安全的陌生代码浏览体验。 Session-level cost：查看聊天会话的总成本，以发现费用较高的对话。 单会话多聊天：在一个 agent host Copilot 会话中并排运行多个聊天。 Workspace trust：在受限模式下安全地浏览新文件夹。...

9. SolonCode v2026.6.24 发布：安全访问、Mermaid 渲染、Goal 重构

• Link: https://www.oschina.net/news/467046/soloncode-cli-2026-6-24
• Source: OSChina AI
• Language: zh-CN
• Published: 2026-06-25
• Matched topics: llm, agent, coding-agent, safety
• Score: 7
• Draft summary: 1、关于 SolonCode（终端编码智能体） SolonCode 是由杭州无耳科技有限公司研发的企业级 终端编码智能体。它是一位全中文驱动的数字员工——能自主理解需求、自主规划步骤、自主编写代码。不挑模型，不挑平台，打开终端就能上岗。 核心差异化：SolonCode vs Claude Code 维度 SolonCode Claude Code 语言环境 全中文引导...

10. Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering

• Link: https://www.langchain.com/blog/agentic-engineering-redefining-software-engineering
• Source: LangChain Blog
• Language: en
• Published: 2026-06-25
• Matched topics: agent, coding-agent
• Score: 7
• Draft summary: Multi-agent systems that mirror real engineering teams — not just code faster — can cut debug time by 93% and compress cross-team delivery. Here's the architecture built on LangGraph.

11. Embed the world: Multimodal AI for searchable aerial imagery at scale

• Link: https://aws.amazon.com/blogs/machine-learning/embed-the-world-multimodal-ai-for-searchable-aerial-imagery-at-scale/
• Source: AWS Machine Learning Blog
• Language: en
• Published: 2026-06-22
• Matched topics: rag, eval, multimodal
• Score: 7
• Draft summary: In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the evaluation methodology we built on OpenStreetMap ground truth, four experiments that compared embedding models, fusion strategies, captioning, and search m...

12. Production-grade AI agents for financial compliance: Lessons from Stripe

• Link: https://aws.amazon.com/blogs/machine-learning/production-grade-ai-agents-for-financial-compliance-lessons-from-stripe/
• Source: AWS Machine Learning Blog
• Language: en
• Published: 2026-06-26
• Matched topics: agent, infra
• Score: 6
• Draft summary: In this post, you learn how Stripe built a production-grade AI agent system for financial compliance. We cover the technical architecture of Stripe’s ReAct agent framework and the infrastructure decisions behind a dedicated agent service. We also discuss the role of human over...

13. NVIDIA Achieves Leading Agentic Coding Performance on First Agentic AI Benchmark

• Link: https://developer.nvidia.com/blog/nvidia-achieves-leading-agentic-coding-performance-on-first-agentic-ai-benchmark/
• Source: NVIDIA Generative AI Blog
• Language: en
• Published: 2026-06-25
• Matched topics: agent, eval, infra
• Score: 6
• Draft summary: AI agents have fundamentally changed the complexity of inference workloads. Until now, the industry has struggled to define a standard for measuring how...

14. How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation

• Link: https://arxiv.org/abs/2606.27275v1
• Source: arXiv cs.CL
• Language: en
• Published: 2026-06-25
• Matched topics: llm, agent, infra, safety
• Score: 6
• Draft summary: Large language models (LLMs) are increasingly critical to digital library workflows, yet their ability to process historical language remains poorly understood. Historical difficulty is typically treated as a monolithic barrier, conflating orthographic variation, linguistic di...

15. The Agent Development Lifecycle: Build, Test, Deploy & Monitor AI Agents | LangChain

• Link: https://www.langchain.com/blog/the-agent-development-lifecycle
• Source: LangChain Blog
• Language: en
• Published: 2026-06-25
• Matched topics: agent, eval
• Score: 6
• Draft summary: Learn how leading engineering teams ship AI agents reliably and repeatedly using a four-phase agent development lifecycle: Build, Test, Deploy, and Monitor. Includes guidance on evals, runtimes, observability, and governance at scale.

16. Daybreak: Tools for securing every organization in the world

• Link: https://openai.com/index/daybreak-securing-the-world
• Source: OpenAI News
• Language: en
• Published: 2026-06-22
• Matched topics: llm, agent, coding-agent, safety
• Score: 6
• Draft summary: OpenAI introduces new Daybreak tools, including Codex Security and GPT-5.5-Cyber, to help organizations find, validate, and patch vulnerabilities at scale.

17. GitLab 19.0将Agentic AI嵌入凭证、合并请求与供应链安全

• Link: https://www.infoq.cn/article/ICdHZotGllYog0ocIrxA?utm_source=rss&utm_medium=article
• Source: InfoQ 中国
• Language: zh-CN
• Published: 2026-06-28
• Matched topics: agent, rag, safety
• Score: 5
• Draft summary: 点击查看原文>

18. Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding

• Link: https://developer.nvidia.com/blog/boost-inference-performance-up-to-15x-on-nvidia-blackwell-using-dflash-speculative-decoding/
• Source: NVIDIA Generative AI Blog
• Language: en
• Published: 2026-06-26
• Matched topics: agent, infra
• Score: 5
• Draft summary: As AI systems move from single-turn interactions to coordinated multiagent workflows, low-latency inference becomes increasingly important. Autoregressive LLMs...

19. Athena 联盟成立：以协同防御应对开源软件安全风险

• Link: https://www.infoq.cn/article/K5kVz7354Na4846mlNsJ?utm_source=rss&utm_medium=article
• Source: InfoQ 中国
• Language: zh-CN
• Published: 2026-06-26
• Matched topics: safety
• Score: 4
• Draft summary: 点击查看原文>

20. Previewing GPT-5.6 Sol: a next-generation model

• Link: https://openai.com/index/previewing-gpt-5-6-sol
• Source: OpenAI News
• Language: en
• Published: 2026-06-26
• Matched topics: llm, safety
• Score: 4
• Draft summary: OpenAI previews GPT-5.6 Sol, a next-generation model with stronger capabilities in coding, science, and cybersecurity, paired with its most advanced safety stack.

21. Claude Fable 5分批重新上线！GPT-5.6秒跟

• Link: https://www.qbitai.com/2026/06/438789.html
• Source: 量子位
• Language: zh-CN
• Published: 2026-06-26
• Matched topics: llm
• Score: 4
• Draft summary: 这不能是营销计划的一部分吧？

22. On owning a codebase, and why it may be the hardest job in software

• Link: http://localhost:5174/blog/owning-a-codebase
• Source: Sourcegraph Blog
• Language: en
• Published: 2026-06-26
• Matched topics: agent, coding-agent
• Score: 4
• Draft summary: AI coding agents are producing more code than ever, but the world still runs on massive, decades-old codebases. Why owning and understanding them may be the hardest job in software.

23. Improving the speed and energy-efficiency of AI agents

• Link: https://news.mit.edu/2026/improving-ai-agent-speed-and-energy-efficiency-0625
• Source: MIT News AI
• Language: en
• Published: 2026-06-25
• Matched topics: agent, infra
• Score: 4
• Draft summary: A new system, known as Murakkab, optimizes the design and deployment of multistep workflows that power AI applications.