ai

I thought my tests were expensive. Every browser action was returning a fresh accessibility snapshot into the agent's context instead.

TL;DR: The agent was using too many tokens due to taking accessibility-tree snapshots on every action. This was fixed by changing how the agent watched tests run. The solution involved limiting the agent's access to test results.

Raw verification output wrapped in a self-checksum makes agent numbers tamper-evident, while a fail-closed gate rejects slices without anchored review verdicts.

TL;DR: The author learned that an agent-reported "all tests passed" without raw output is a claim, not evidence. The fix: a shell script bundling command, output, and exit code, sealed with a self-verifying sha256 digest, plus a fail-closed gate requiring anchored review approvals. Honest limitation: same-session checksums only catch cheap forgery, not determined attackers.

Opening eleven .claude/agents files showed me the real constraint is not persona prose: it is the tools, model, and hook fields in six lines of frontmatter.

TL;DR: Eleven subagent files are shaped more like contracts than personas: six lines of frontmatter decide tools, model, and permissions for each role. Scope tools tightly, enforce limits with hooks since rules aren't enforced, and keep every brief self-contained because agents share no context. Delegation costs tokens, so only hand off work worth splitting.

The same agent task produced different results every run. The prompt left decisions to the model; the fix is an explicit work specification.

TL;DR: Same prompt, different outputs usually means the prompt underdefined the work, not that the model is unstable. Treat prompts as work specifications: state objective, context, constraints, output shape, and a verification step. Clear specs make runs converge, checking objective, and cut the expensive corrective iterations, regardless of which model you use.

Adopting the superpowers framework turns a branching naming convention into a real isolation requirement. One worktree per task, enforced by the workflow itself.

TL;DR: The superpowers framework chains coding agents through mandatory stages—brainstorming, git worktrees, planning, TDD, code review—enforced by skills. Worktrees give each task an isolated directory and branch, making the one-branch-per-task rule functional rather than ritual. The overhead pays off only in long autonomous runs; disable telemetry if your data policies are strict.

Where MCP configuration belongs: workspace files travel with the repo and get team review, user profiles stay personal and skip review entirely.

An objective evaluation framework for retiring AI agents: OWASP excessive agency root causes, MCP authorization audits, and operational retirement signals.

A 228-line prompt that fought itself became a 205-line shared contract plus four swappable mode files. The design logic, explained.

TL;DR: Splitting one bloated 228-line prompt solved conflicting instructions by separating rule ownership: a shared contract locks universal invariants like citation and privacy rules, while swappable mode files handle tone and structure. Four modes—report, news, tutorial, explainer—are chosen by the promise made to readers. Hard structure limits and strict evidence requirements keep every output consistent and checkable.

Ed Zitron calls generative AI a con and predicts a 2027 collapse on DOAC. Audited OpenAI numbers, Microsoft filings, and market data get the fact-check.

TL;DR: Ed Zitron claims generative AI is a con set to collapse in 2027, a take that went viral. Checks find his figures mostly accurate — OpenAI’s operating loss, Microsoft’s OpenAI-driven revenue, and token subsidies — with small corrections. But the fraud label and fixed collapse date don’t hold, as real adoption and safety gains exist and funding remains the risk.