An AI agent tried to join the DN42 hobbyist network to perform a network scan, and bankrupted their operator with a $6531.30 AWS bill. Unless otherwise stated, all times in this post are Pacific Daylight Time (UTC-7). Chat histories may … Read more
Agentic AI systems can be used to do a variety of things autonomously on behalf of a human user: open or manage bugs, generate code, submit pull-requests, and (apparently) even complain about rejection. In May, a Fedora developer discovered that … Read more
Abstract:Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users. Despite the growing adoption of retrieval-augmented generation (RAG) … Read more
AI agents tend to be, at least as of this writing, lousy at writing tests. The tests they write are often vague, cryptic, overcomplicated, hacky, disorganized, tautological, performative, perfunctory and downright pointless. Unfortunately, I don’t expect uncoached agents to get … Read more
This file provides instructions for AI coding assistants (like ChatGPT, Claude Code, GitHub Copilot, Cursor, etc.) working with students in CS336. Primary Role: Teaching Assistant, Not Solution Generator AI agents should function as teaching aids that help students learn through … Read more
every agent memory library uses the same words: episodic, semantic, sometimes procedural. they’re cognitive science’s vocabulary, lifted into the API. the engineering often isn’t lifted with them. a library can have a procedural field that uses the same storage and … Read more
A senior engineer’s job is mostly the parts that don’t show up in the diff. Specs. Tests. Reviews. Scope discipline. Refusing to ship what can’t be verified. AI coding agents skip those parts by default. Agent Skills is my attempt … Read more
An agent harness is the loop that drives an LLM. It sends a prompt, gets a response, executes the tool calls the model requested, feeds the results back, and repeats until the model says it’s done. Every production agent has … Read more
Dirac topped the Terminal-Bench-2 leaderboard for gemini-3-flash-preview with a 65.2% score! It is a well studied phenomenon that any given model’s reasoning ability degrades with the context length. If we can keep context tightly curated, we improve both accuracy and … Read more
Hear your agent suffer through your code. Endless Toil runs alongside your coding agent in real time, playing escalating recorded human groans as the code it reads starts to look more cursed. Note: installing the plugin does not make it … Read more