The bug that doesn’t fail any test Karl Tryggvason has been building In the Long Run, an app that projects your accumulated Strava mileage onto famous long-distance routes around the world. Think: your training log, plotted against the Pacific Crest Trail or a Trans-Europe path. The mileage becomes progress. He wanted the routes to feel alive. Not just lines on a map — places, landmarks, the small historical detours that make a thousand-mile run feel like more than a thousand miles. ...

Yesterday (June 23) Anthropic published Introducing Claude Tag on the Newsroom. The post is short, but somewhere in the middle there’s a line I read twice: Today, 65% of our product team’s code is created by our internal version of Claude Tag. Sixty-five percent. Of the code Anthropic’s own product team writes, 65% is written by Claude Tag. The source matters here. This isn’t a customer case study. It’s Anthropic dogfooding the thing, then publishing the number. It’s the same release pattern they used for Claude Code Artifacts on June 18. Anthropic ships only after the workflow has been chewed on internally long enough to be embarrassing not to. ...

The top of Hacker News yesterday belonged to a hardware post. Steam Machine launches today finished at 1201 points, 1085 comments, and held the #1 slot for the better part of 24 hours. That is not a legendary HN score, but it is a notable one in 2026, an environment where AI tooling tends to dominate the front page. A gaming console announcement out-crowding the agents is itself the story. The submission came from theschwa (Michael of SteamDB) and pointed at the official Valve press release: $1049 base, SteamOS, an AMD Zen 4 + RDNA3 semi-custom SoC, 16GB system RAM, 8GB GDDR6 VRAM. ...

If you have built any non-trivial agent or RAG pipeline, you have probably been shocked by an API bill at least once. Not the training-side cost. The “every call stuffs a wall of context into the prompt” cost. For me it was Claude Code sessions: the tool outputs, the build logs, the RAG chunks I had been dumping in raw, then paying for by the million tokens. Then I ran into chopratejas/headroom, currently sitting at the top of GitHub’s monthly trending list with +41,093 stars this month. Its tagline reads: ...

If you only read feature comparison tables, Codex and Claude Code differ in thirty places: model choice, browser support, rate limits, phone handoff. That is not what I want to write about today. Today I want to write about a 350-like tweet, and the two core maintainers standing next to it. The tweet that broke the silence Peter Yang (@petergyang) writes the Practical AI tutorials newsletter, 150K+ subscribers. At 3:32 AM UTC on June 20, he posted: ...

The most expensive thing about being an AI engineer is not the model calls. It’s the meetings about the model calls. On 2026-06-18, Anthropic pushed out Claude Code Artifacts, and the timing feels deliberate. The product story they tell is small: a developer kicks off an incident investigation in Claude Code, and the agent publishes a page as it works. By the time standup starts, the page has refreshed twice, and the team is staring at the same URL instead of asking someone to walk them through what the agent found. That pitch is the entire reason I wanted to look at this. ...

On the evening of June 18, the official Model Context Protocol blog published Enterprise-Managed Authorization: Zero-touch OAuth for MCP. Core maintainer Paul Carleton kept the tone measured, but the news was substantial: the EMA extension moved from draft to stable, and it crossed 226 points on Hacker News within hours. The same day, Anthropic, Microsoft, and Okta endorsed it; Asana, Atlassian, Canva, Figma, Granola, Linear, and Supabase all flipped on support, and Visual Studio Code wired it into the IDE. ...

Yesterday the front page of Hacker News led with GLM-5.2 is the new leading open weights model on Artificial Analysis: 858 points, 417 comments. The submitter, himata4119, was new. The source wasn’t: it is the Artificial Analysis Intelligence Index v4.1, the third-party benchmark the rest of the AI world uses to seat frontier models. Six months ago, a story like this would have collected a few “propaganda” replies on HN. This time it didn’t. I read the top 30 comments. The technical folks were comparing Elo scores, $/M token, context windows, and rate limits. No one was discussing who made it. ...

On June 16, Vicki Boykis’s “Running local models is good now” hit Hacker News at #4 — 1044 points, 437 comments. Her machine is a 2022 M2 Mac, 64GB of RAM, 1TB of storage. Not an M3 Ultra workstation. The boring developer default. But Vicki did one useful thing in the post: she defined a personal vibe metric — “am I still double-checking against a cloud API?” — and then admitted that after GPT-OSS she does that “a lot less often,” and with the latest Gemma 4 release she can finally run local agentic coding loops at roughly 75% the accuracy and speed of frontier models. ...

On June 11, Show HN: Fata – Spaced repetition to fight skill rot from AI coding hit the front page of Hacker News, with 75 points and 44 comments. Fata itself is a kind of Duolingo for code: 5–10 minutes a day of spaced repetition on Rust, CSS, React, Python, TypeScript, and Architecture, runnable in the browser with no signup required. But the thing that actually caught my attention is not Fata. It is how the author describes himself. ...