158K lines of AI-generated C# for a Cities: Skylines II total conversion mod. CivicRAG for codebase indexing, 300+ custom Roslyn analyzers as compile-time design rules, and manual visual debugging for render bugs AI couldn't see.
CVE-2026-26268, fixed in Cursor 2.5, allowed AI agents to rewrite insufficiently protected .git config and Git hooks, leading to out-of-sandbox RCE on the next Git operation.
ZDI-26-305 discloses a sandbox bypass in OpenAI Codex. Processing a repository containing malicious JavaScript can lead to code execution under the user's privileges outside the sandbox.
Designing field-level confidence thresholds for human-in-the-loop document extraction, and the OCR and threshold walls hit when automating journal entries with freee MCP.
Playwright MCP v0.0.71 added browser_drop. MCP clients can now invoke Locator.drop directly, reducing the need to fake drag-and-drop via evaluate or mouse.move chains. Covers intermediate event firing and screenshot verification of CSS changes during drag.
ERC-8128 emerged as a standard for proving the origin of AI agent communications when agents handle crypto assets. Walks through ERC and message signing basics, how it differs from API keys and OAuth, and the implementation flow.
A look at sachitrafa/YourMemory, a local MCP memory server combining Ebbinghaus forgetting curves, BM25, vector search, and graph expansion. LoCoMo-10 Recall@5 currently sits at 59%.
An LLM safety monitor's evaluator can be tricked into clearing dangerous sessions when the attacker plants fake analysis text in the monitored conversation. Experimental results, defense limits, and structural separation points.
Rethinking the evolution of CLI, GUI, chat UI, and AI agents as interface design for the development workflow. Covers why CLI rather than CUI emerged as GUI's counterpart, and the context-window cost difference between MCP and CLI.
A look at WUPHF's LLM wiki that trended on Show HN. Using Markdown as the source of truth with Git history, SQLite, Bleve, and lint for shared agent memory is a different bet from RAG or managed memory.
Reading Anthropic's postmortem and the DEV operational report in the same week reveals that Claude Code's quality degradation and Max weekly quota exhaustion are not separate incidents—they're two sides of the same quality×cost design decisions. A timeline and operational priority walkthrough.
