AI

Reading my feed on July 2 and 3 — Hacker News, X, blogs, WeChat — five engineering tips connected themselves into a single line in my head. The line used to live scattered across sources without anyone naming it. When it surfaced in 24 hours, it became hard to ignore. I am not going to write an “agent tool roundup” today — I did that on June 28 with a five-layer stack. That was the map. This piece wants to be the signposts. The thesis is simple: five teams that actually use agents in production hit the same wall in early July. They each gave their own answer. I want to put those answers on the same page and see what is shared. ...

I need to start by correcting something I wrote on June 5. In Anthropic’s overnight triple move: building agents and containing them at the same time, I read Anthropic as a company running “two parallel lines” — a public “contain Claude” engineering program and a quieter recursive-self-improvement research track — and concluded that Anthropic was the safety-first operator, walking a “guardrails first, then capability” path. I had three pieces of evidence: an open-source vulnerability discovery framework, a recursive self-improvement research post, and the engineering article “How we contain Claude across products.” I read those three together and concluded Anthropic’s engineering culture was more credible than OpenAI’s. ...

I am writing this on the morning of June 30, 2026. The last day of June. If I had to summarize the most important engineering shift in AI in the first half of 2026 in one sentence, I would not say “the models got bigger” or “context windows got longer.” I would say: the protocols around agents are starting to grow up the same way the protocols around the web did in 1995. ...

AI agents are not one category anymore. That is the most confident thing I can say after a week of radar pulls. As of June 28, every agent-flavored project that consistently lands on the GitHub monthly leaderboard, the Product Hunt monthly leaderboard, or the HN weekly leaderboard has settled into one of five layers. Each layer has its own champion, its own growth curve, its own user base. The five: research, memory, orchestration, anti-slop, evaluation. This post lays the map flat, then explains why “separated cleanly” matters more than “built strong.” ...

On the afternoon of June 26 (U.S. Eastern), OpenAI published a preview post for GPT-5.6 Sol on its blog, and parked the system card at deploymentsafety.openai.com. The same day, the Washington Post reported that the U.S. government will decide which users get access to GPT-5.6. The same day, Reuters reported Anthropic is releasing Mythos only to “trusted partners.” Three events, less than 24 hours apart, each individually heavy. I am not going to write “AI regulation is here” — that ground was covered on June 14 in AI regulation just walked into the product. What I want to do today is zoom in much closer: what does GPT-5.6 Sol’s launch actually change, for a normal user, a normal builder, a normal product spec writer. ...

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. ...

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. ...