{"date":"2026-07-11","title":"What happened in AI — Jul 11, 2026","generated_at":"2026-07-11T21:11:41Z","intro":["A quiet day for launches, but a consistent thread in what builders shared: tooling to make agents auditable rather than just capable. Two separate builders arrived at the same recipe for a trustworthy LLM judge — a human-audited rubric scored by a prompt, validated against human labels before it's trusted — while coding-agent tooling focused on giving agents richer context and letting builders supervise them remotely instead of blindly.","One more data point on cost: a naive Wikipedia fetch runs past 68,000 tokens, and today's fix was purpose-built extraction, not a bigger context window."],"highlights":["Vasari and HackerRank's hiring agent both converged on the same judge recipe: rubric to prompt, validated against human labels before trusting it in production.","Agentation turns a clicked UI element into a CSS selector, source file path, and component tree an agent can grep directly.","AgentKindergarten tunnels a coding agent's terminal to your phone with no inbound firewall rules, plus auto-flagging when a session stalls.","A naive Wikipedia fetch costs 68,240 tokens; a new stealth-browser MCP cut a blocked page down to about 700."],"article_count":5,"categories":[{"name":"Coding-Agent Tooling","slug":"coding-agent-tooling","summary":"Two new tools treat the coding agent itself as fixed and build the tooling around it: one turns visual UI feedback into machine-readable context, the other streams and remotely supervises an agent's terminal session.","articles":[{"title":"Agentation – Visual UI Annotation for AI Coding Agents","summary":"Click a UI element, add a note, and the agent gets the CSS selector, source file path, React component tree, and computed styles instead of a vague description like \"the blue button.\"","source":"hackernews_ai","url":"https://www.agentation.com/","published":"2026-07-11T16:16:51Z"},{"title":"AgentKindergarten – daycare for your AI coding agents","summary":"A daemon-relay-client setup tunnels a coding agent's terminal and auto-detected dev-server ports to a phone or browser with no inbound firewall rules, plus a report-card grader that flags stalls and errors automatically.","source":"hackernews_ai","url":"https://github.com/rokrak1/agentkindergarten","published":"2026-07-11T10:08:05Z"}]},{"name":"Building Trustworthy LLM Judges","slug":"building-trustworthy-llm-judges","summary":"Two unrelated builders landed on the same recipe for a judge you can actually trust: a human-auditable rubric turned into a score by a prompt, only relied on after checking it against human-labeled ground truth.","articles":[{"title":"I built a free tool to evaluate AI agent outputs (human labels and LLM judges)","summary":"Vasari has reviewers label agent traces pass/fail with error codes, then validates any LLM judge against those human labels with a confusion matrix and Cohen's kappa before it's trusted on unlabeled production traffic.","source":"hackernews_ai","url":"https://github.com/AntoineF23/verdict","published":"2026-07-11T19:55:44Z"},{"title":"Inside HackerRank's LLM-based Hiring Agent","summary":"The pipeline scores resumes on a fixed rubric (up to 35 of its points for open-source contributions, excluding a candidate's own repos) computed almost entirely by prompt templates rather than hardcoded logic — testing found its startup-founder bonus barely moved scores.","source":"hackernews_ai","url":"https://blog.grandimam.com/posts/how-hacker-rank-scores-engineers/","published":"2026-07-11T07:43:55Z"}]},{"name":"Context & Tool-Use Economics","slug":"context-tool-use-economics","summary":"Naive page fetching can cost an agent tens of thousands of tokens per page; today's fix on display was extraction tooling purpose-built to strip that overhead before it ever reaches the model.","articles":[{"title":"One Wikipedia page costs your AI agent 68,000 tokens","summary":"An average Wikipedia article runs 68,240 raw-HTML tokens to fetch, and Claude Code's own web tool falls back to near-empty results on JS-heavy or anti-bot pages — prompting an open-source stealth-browser MCP that cut one blocked page's cost from a 403 error to about 700 tokens.","source":"hackernews_ai","url":"https://news.ycombinator.com/item?id=48867021","published":"2026-07-11T00:12:26Z"}]}]}