Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
SWE-sweep: Can Agents Autonomously Find and Fix Bugs?
Meta Superintelligence Labs and academic collaborators introduce SWE-sweep: agents must discover and repair latent bugs across 100 real repositories (~4.1k bugs) with no issue hints—early leaders resolve under 5%, highlighting bug finding as the hard part.
6 min · 1,411 words
AI-powered fuzzing with the GitHub Security Lab Taskflow Agent
Antonio Morales walks through GitHub Security Lab’s Fuzzing Taskflow: point it at a C/C++ repo and an LLM agent writes harnesses, runs AFL++, reads coverage, triages crashes, and files reports.
9 min · 2,147 words
Meet Compass: Wealthsimple’s AI Teammate
Wealthsimple’s engineering team introduces Compass, an AI teammate that lives in Slack—what it does today, how they built it, and how it is becoming a fast friend for the company.
4 min · 846 words
Jared Norman responds to DHH’s Rails World 2026 keynote: Rails still under DHH’s control, how AI agent coding changes the framework’s role, and why Rails developers cannot ignore his vision.
9 min · 2,017 words
Agentics: what is developer process automation?
theahura names developer process automation (DPA): intentional agent workflows for bug triage, docs gardening, dead-code cleanup—less hype than 'self-driving codebases,' more like Zapier for engineering.
6 min · 1,268 words
Mistral Vibe Permission Bypass and Arbitrary Code Execution
SecMate details CVE-2026-87987 and CVE-2026-87984 in Mistral Vibe: shell permission bypasses that let a coding agent reach arbitrary code execution when those controls are treated as a security boundary.
7 min · 1,648 words
AWS’s Matt Wood argues AI agents change ops from “is it broken?” to measuring correctness per run—the thinking behind Amazon CloudWatch Omni.
5 min · 1,214 words
How to serve trillions of tokens for trillion-parameter coding agents
Modal explains how it serves coding-agent inference at extreme scale—performance and efficiency techniques for trillion-parameter models generating trillions of tokens, written for teams facing the same workload.
30 min · 6,972 words
Electric Capital open-sources Quest, a safety-first AI harness that keeps sensitive data inside your perimeter unless a user explicitly approves outbound access—Apache 2.0 on GitHub.
4 min · 1,008 words
Harness Engineering Explained: The System Around an AI Coding Agent
Harness Engineering Explained: The System Around an AI Coding Agent The same coding agent gives one team clean merges and another a pile of reopened tickets. The difference is rarely the model. It's the six parts around it, checked one ticket at a time.
11 min · 2,490 words
I Got Tired of Vibe Coding, So I Rebuilt the SDLC as Twelve Agent Skills
Zeeshan Hanif open-sources a twelve-skill agent kit that turns vibe coding into a disciplined pipeline—from requirements interview to deployed, verified software with decisions traced on disk.
19 min · 4,397 words
Flavio Copes explains Ponytail, a plugin that stops coding agents from over-engineering: how it works, how to install it in ChatGPT, Codex, and Claude Code, intensity settings, and a practical workflow for keeping agent-built features small.
10 min · 2,212 words
Frequently Asked Questions (And Answers) About AI Evals
Hamel Husain and Shreya Shankar’s sharp FAQ on AI/LLM product evals: start with error analysis on real traces, build targeted evaluators, validate LLM judges with TPR/TNR, and avoid generic off-the-shelf metrics.
74 min · 17,016 words
Semantic memory or just Markdown?
Laravel Boost tried embeddings and semantic search for project rules, then deleted them: a generated Markdown index plus grep proved simpler and more reliable for teaching agents existing conventions.
7 min · 1,562 words
Pencils Down, Eyes Open: A Rails Developer After Rails World
A longtime Rails developer sits with DHH’s Rails World keynote declaring the end of routine hand-coding—what feels lost, what might be gained, and how to stay useful when agents write the default path.
4 min · 998 words
Sunil Sadasivan on first-principles thinking for senior engineers working with AI agents: set experience aside long enough to see the problem clearly, then rebuild judgment on top of how agents actually work.
3 min · 624 words
Last week I wrote about using AI to edit my videos. My first try was five paragraphs describing WHAT I wanted and HOW I wanted it done. I expected it to one-shot the rest. A lot of people like to talk about one-shotting a task with AI.
2 min · 435 words
Claude Code reads AGENTS.md only when telemetry is on
Przemek documents that Claude Code 2.1.277’s AGENTS.md loader sits behind a remote feature flag: with telemetry or nonessential traffic off, a local AGENTS.md is skipped silently—what he measured and a one-line CLAUDE.md workaround.
4 min · 1,002 words
Why Claude Opus 5.5 Still Won't Fix Your AI Agents
VooStack argues that swapping in a stronger LLM won’t fix unreliable agents: the real work is orchestration, observability, and API design—the engineering discipline required to ship agents that hold up.
7 min · 1,545 words
Bots for the last mile: Rollouts, Security Review
Cursor ships Rollouts (PR-to-production change monitors with regression actions) and Security Reviewer (context-aware vuln findings with fixes) for Teams and Enterprise.
2 min · 528 words