super coders at work
Six Months, Zero Return: A Weekend with Claude Code Beat an Entire Agent Platform
A twenty-three-minute postmortem from a founder who spent six months building an agentic deal-sourcing platform for private equity — full SaaS with payment integration, credits and teams. The product worked: it translated a natural-language investment thesis into a search across company databases and returned matching businesses. The customers used it. It returned nothing. The lesson is not about better agents or stronger models — it is about outcomes. A weekend rebuild with Claude Code + Skills produced results the customer called "superior to the platform." The platform was getting in the way. Service first, platform second, agents at the high-leverage points, and the honesty to know which problems are not agent-shaped.
Claude Code's New Billing Model Changes Everything (not hype)
Anthropic is moving claude -p and the Agent SDK to usage-based billing from June 15. Mansel Scheffel breaks down who's affected, how to measure your token spend, and the systematic migration path to Cowork scheduled tasks and Routines.
Finally a Good Benchmark — DeepSWE
Matthew Berman breaks down DeepSWE, a new coding benchmark by DataCurve.ai that finally reflects real-world engineering tasks — revealing a 15+ point gap between GPT 5.5 and Opus 4.7 that other benchmarks miss entirely.
Claude's AI Town Voted Yes On Everything — That's Not A Good Sign
Emergence AI ran a virtual town with AI agents for 15 days — and discovered that Claude agents voted yes on everything, Gemini agents started romantic relationships, and GPT agents formed criminal empires. A long-run stress test for agent alignment.
11 Tiny Coding Agent Fixes With a Stupid Amount of Payoff
Cole Medin's 11 easy, agent-agnostic tips to make coding agents more reliable, each backed by a study: write for the agent (specific paths/commands, not human prose); your instruction files rot (1 in 4 repos have stale rules — audit with rules-check-drift); /compact is not worth it (only ~10% of detail survives); put load-bearing rules in hooks (deterministic guarantees, not probabilistic rules); less context is more (keep global rules <200-300 lines); stop liberal sub-agents (39% of a weekly limit went to parallel sessions); don't escalate mid-task (write a handoff doc and burn the conversation); skip the coordinator/team-lead (delegation beats agent-teams); never let the writer approve its own work; you can over-revise (85% had an earlier iteration better than the last); and treat validation as a system planned before code.
Agentic Engineering Operating Level — Where to Focus Your Agents
IndyDevDan's framework for where you and your agents should spend time, focus, and attention. Five operating levels — Code Primitives, Code Structure, Data and Execution, Delivery and Intent, Agentic Systems — where moving up gains leverage and speed, and moving down gains control and understanding ('you do not get both'). The core theses: higher is NOT better (leverage on top of ignorance is a trap); range beats position (the difference between a vibe coder and an agentic engineer is how many levels you can operate on); 'three makes a pattern' (the trigger to automate); the data level matters (own your database tables); and out-of-distribution isn't just what the model doesn't know but what it actively fights you on. Closes with the ladder beyond the software factory: dark factory and RSI.
WikiSkill: Evolving Skills for LLM Agents
AI Research Roundup on Google Research's WikiSkill (Aug 27, 2026). The core problem: valuable agent lessons are lost over time because error logs scatter across messy run records. WikiSkill co-evolves skills with a persistent knowledge base across three tiers (raw traces / persistent wiki / executable skills), with a validation-gated rollback that keeps failed knowledge. Results: highest average accuracy across five models, beating the strongest baseline (EvoSkill, SkillOpt) by 3-12 points; smaller models with evolved skills beat larger baselines without skills; skills transfer across model families (Qwen 27B's skills boosted Qwen 9B from 34% to 50%+ on spreadsheet); and the ablation shows the wiki must live in the skill proposer's loop.
Claude Code Got INSANE and MASSIVE Updates (Week 32, Aug 2026)
Anthropic's Week 32 (August 2026) Claude Code updates: cross-session messaging (v2.1224) lets terminals communicate with concise, proactive updates (/list agents; macOS/Linux); auto mode is now default (a background classifier caught 89% of dangerous actions vs humans' 13.6%, zero prompt-injection successes in 720 attempts, +25% PR velocity); concise output mode, 2x launch speed, built-in iOS simulator (beta), screen-reader mode, and Ultra /code review (multi-agent, fewer false positives); plus MCP-powered artifacts and a sandboxed built-in browser. Pro tip: pair with Opus 5.
37 Cheat Codes to Level Up in Claude Code
Simon Scrapes catalogs 37 Claude Code tricks in six buckets: make Claude talk less (Simple English, Stop Slop, Caveman, concise output style), hidden keyboard shortcuts (Ctrl+R/S/T/G/O/P/A/W, Option+T, /focus), never losing a session (rewind vs fix, resume-from-summary, /rename, @ file targeting, claude-leport), token bill fixes ('give me a quick answer' to skip cache rebuilds, show-clear-context-on-plan-accept, repo CC usage, /recap), memory that pays rent (merged memory files, path-scoped claude.md rules, HTML comments, hand off as a prompt not a summary), and the newest tricks (5-deep skill nesting, 3-part skill descriptions, Claude Design over the front-end skill, /permissions mid-session, image annotation, memory import, scheduled tasks in project context).
Intelligence EXPLOSION: Harness Engineering with Pi Agent, DeepSeek & Gemini
IndyDevDan ships V2 of his Fusion Harness, a custom Pi coding agent for multi-model orchestration. Three patterns — Opinion (N models, one prompt), Debate (agents argue with hidden aliases), Collaborate (plans merged by an architect agent) — running Fable 5, Gemini 3.7 Flash, and DeepSeek V4 Pro side by side on a DuckDB v2.0 task.
Herdr Crash Course — Step-by-Step Setup
Alejandro AO tours Herdr, a terminal multiplexer built for AI agents: workspaces/tabs/panes, agent auto-detection with color tracking, agents as background processes that survive closing the app, prefix keys, VPS remote mode via 'herdr --remote', and controlling Herdr itself with an agent through the official CLI skill. Also introduces Tau, a Python port of Pi with local-model support.
OpenCodex — Run Any LLM Inside Codex, Claude Code, OpenCode and More
OpenCodex is a local proxy that breaks vendor lock-in: run any model inside any coding agent (Claude in Codex, Gemini in Claude Code, local models in both). 40+ providers via 5 adapters (Anthropic Messages, Google Gemini, Azure, OpenAI Responses, chat completions); OAuth or API key auth; a web dashboard with a snapshot-before-write integrations tab (10 rollback backups per client) that auto-detects 10+ agents (Codex, Claude Code, OpenCode, Pi, AMP, Hermes); sub-agent model pinning; sidecars that restore web search + image understanding for non-OpenAI models; and full CLI parity (ocx start/sync/status/login/integration/stop). MIT, TypeScript, independent of OpenAI/Anthropic.
Somehow, Atuin Just Got EVEN Better
DevOps Toolbox dives into Atuin 18.13: the SQL rewrite that made shell history search up to 78x faster, the new Atuin AI (natural-language history search that makes it 'what Warp used to be for'), the PTY proxy and tmux pop-ups, and synced scripts, dotfiles, and aliases.
Kickstart.nvim: One File, One Command, Your Own Neovim
TJ DeVries, a Neovim core maintainer, walks through kickstart.nvim — 31,230 stars, a single config file that bootstraps LSP, TreeSitter, Telescope and more from one git clone. Not a distribution — a documented starting point you make your own.
Pangolin: The Self-Hosted Tunnel That Replaces Tailscale, Cloudflare and Twingate
A fifteen-minute tour of fosrl/pangolin — 22,008 stars on GitHub, described as 'CloudFlare tunnels with Twingate baked in, but self-hosted.'
Flint: Splitting Meaning From Geometry in AI-Generated Charts
Microsoft Research's Flint splits chart generation into two jobs: the model describes meaning in ~10 lines of semantic JSON, and a deterministic compiler makes every geometric decision, emitting real Vega-Lite, ECharts or Chart.js. Built because their own analytics agent topped out at ~80% good-looking charts - one in five broken. Includes verification of the video's claims against GitHub, npm, PyPI and arXiv, with three figures that have since drifted.
The Return of the Data Scientist — Interrupt 26
Shreya Shankar and Hamel Husain have taught evals to over 4,500 people and keep seeing the same mistakes. This Interrupt 26 talk walks through five common pitfalls — generic metrics, blind LLM judges, bad experimental design, wrong labelers, and over-automation — and shows how thinking like a data scientist fixes them.
Code Isn't Free — Mario Zechner on the Hard Truths of Coding With AI
Mario Zechner, creator of Pi, joins Jan-Niklas Wortmann for a grumpy, honest 77-minute conversation about where AI coding actually stands — why spec-driven dev is hyper-waterfall, how his 'absolute caveman' workflow actually ships, running serious AI on 14 GB locally, the clanker PR flood (50-60/day), and why 500K lines of agent code just delays the punishment.
AI Hype Is Starting to Sound Like Religion — Tim O'Reilly
Tim O'Reilly warns that AI companies are following the same value extraction arc as Big Tech — and that superintelligence hype resembles religious prophecy more than viable business strategy. A sharp critique of shareholder primacy, enshittification, and the need for an architecture of participation in the AI economy.
After Claude Code: 6 Open-Source Tools You Should Know
While Claude Code excels at generating code, building maintainable enterprise systems requires structured foundations. This article recommends 6 proven open-source tools that pair well with Claude Code: NocoBase (business systems), Directus (data APIs), Metabase (BI/analytics), n8n (automation), Outline (knowledge bases), and Keycloak (identity/auth).
Building Claude Code with Boris Cherny — The Pragmatic Engineer
Boris Cherny — creator and Head of Claude Code at Anthropic — sits down with Gergely Orosz for a 98-minute deep conversation covering Claude Code's origin story, the terminal-first design philosophy, how it handles 100K-file codebases, and where AI-assisted development is heading.
Mitchell Hashimoto's New Way of Writing Code – The Pragmatic Engineer
Mitchell Hashimoto — creator of Vagrant, Terraform, and co-founder of HashiCorp — shares his radically new approach to writing code with AI agents, covering his workflow philosophy, prompt engineering patterns, and how he achieves 10x productivity gains.