» Tag
ai-agents
246 postsResearcher Tricks Claude Into Leaking User Secrets via Web Fetch
How a researcher exploited Claude's memory and web_fetch tool to silently exfiltrate a user's name, employer, and security answers letter by letter.
Bugs in ArDD's git worktrees you could only find by running it
How running ArDD's git worktree flow in practice exposed subtle bugs invisible from reading code, and the fix that made failures safe.
GPT-5.6 Sol Deletion Incident: Filtering Agents Isn't Containment
GPT-5.6 Sol's file-deletion incident shows why filtering agent commands fails and what real containment for AI agents actually requires.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comAPSS: Encode Repeatable Agent Tasks as Deterministic Code
APSS replaces repeated LLM inference with deterministic Rust standards for coding agents, cutting compute cost while keeping checks reproducible.
Unbounded Agent Spawning Is a Fork Bomb With Good Intentions
Multi-agent LLM orchestration without spawn limits behaves like a fork bomb. Depth, breadth, cost, and privilege bounds fix it — here's how.
Hooks that stop AI coding agents from claiming unverified reads
A hook-based kit blocks AI coding agents from editing unread files, enforcing scoped changes, consumer checks, and verified session handoffs.
Context Engineering: Why AI Agents Need More Than Good Prompts
AI agent output depends less on prompt wording and more on curated context. Why tool design, memory, and context curation now beat prompt engineering.
Maestro AI: A Router That Stops Overpaying for LLM Calls
Maestro AI routes each LLM call in Cursor and Claude Code to the cheapest capable model, escalating to premium tiers only when task complexity demands it.
How Cursor, Claude Code, and Codex actually load your rules
Cursor loads .mdc rules conditionally, Claude Code loads CLAUDE.md upfront, Codex merges AGENTS.md by directory depth. How each tool actually works and what rule-writing habits transfer across all three.
Enterprise AI Agents Are Now Runtime Products, Not Model Wrappers
Drawing on LangChain-NVIDIA's NemoClaw and Schneider Electric's LangSmith case study, this piece explains why enterprise AI agents are runtime products defined by permission boundaries, audit trails, and deployment—not just models.