Google’s AI Mode said a UK travel permit is embedded in your passport chip. That is false, and it is built from two true sentences on GOV.UK. Here is how a fact changes each time it is copied, why the copies now get the credit, and what it takes for a fact to carry its source.
Karpathy’s autoresearch and DeepMind’s AlphaEvolve improve things with one simple loop: propose a change, score it, keep it only if it wins. I ran the same loop three ways: on trading strategies with a backtest as the scorer, on a spec and a strategy with LLM judges as the scorer, and by hand through 56 LLM review panels. The backtest loop inflated its own results 3 to 4 times. The LLM-judged loops stalled and learned to flatter the judges. Here is what each failure teaches, and how to build a loop that works.
South Korea put light green licence plates on expensive company cars in 2024 to stop owners from driving supercars on business tax deductions. The plates cut registrations by a third in the first year and turned into a badge of wealth in the second. The tax office now audits from the list they created.
For months I have sent every Russian translation through Gemini, because Claude’s Russian reads like American English. I assumed Google’s search index was the reason. The data says Gemini really is ahead, but the lead is one year old, and it is not the index or the tokenizer.
I asked my AI agent to plan a family escape from Chiang Mai’s burning season. It reverse-engineered a proprietary air quality encoding, scraped flights, checked fuel costs, and compared 15 cities across 10 years of data. This is what Web 4.0 actually looks like: open databases + agents that query them.
Skills don’t reliably auto-invoke. We built a three-layer system: searchable learnings files, a curation skill, and a post-commit hook that reminds you to document.
An entire infrastructure layer (CSS, JS, frameworks) is becoming optional for a growing class of consumers. Here’s how to serve markdown via HTTP content negotiation.
Your competitor uses Claude or GPT to move faster. If you don’t, you fall behind. That’s the trap.
The Best Agent Architecture Is Already in Your Terminal My project’s CLAUDE.md file had grown to 55KB—242 learnings crammed into one massive file. The problem? Claude prepends this file to every single prompt. A 55KB context file means less room for thinking and acting. Sessions hit context limits faster. Compaction happens sooner. I noticed the degradation: sessions became noticeably shorter, context compaction triggered more frequently, and the agent seemed to lose track of longer conversations. ...
The iteration trap is really a clarity trap. You iterate because you don’t know what you want.