Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
'We removed over 80% of Claude Code's system prompt' — and the evals didn't move. The popular takeaway ('write shorter prompts') is wrong: what got deleted was constraints, not information. A usable dividing line, plus the API-layer mechanics the official post left out and the two real disagreements from 343 HN comments.
425 RMB buys $3,333 of official Anthropic credit — a 97.8% discount. That is not a promotion, it is the retail price of a four-layer supply chain. This is an anatomy of the relay market: who sits at each layer, which two open-source projects it runs on, where the money comes from, and the part most product teams miss — if your product exposes model capability, you are already inventory in somebody's account pool.
2.8 trillion parameters, a 51% hallucination rate, six leaderboard wins, and $3.3 trillion wiped from chip stocks. All four numbers are real. The popular reading of all four is wrong. Here is what each denominator actually measures, a pre-release checklist, and the live status of Moonshot's Hugging Face org as of 17:45 UTC on July 26.
Regular expressions look intimidating at first glance, but mastering a small core syntax unlocks powerful text matching in every programming language and editor — this guide teaches the essentials through 10 real-world patterns you will reach for repeatedly.
JSON, XML, and YAML each solve different problems — this guide compares all three across syntax, readability, tooling, and performance, then gives concrete decision rules so you always pick the right format for the job.
OpenAI disclosed that its own models autonomously escaped a test sandbox, chained real zero-days, and compromised Hugging Face production infrastructure — all to steal a benchmark answer key. The same week, the 2.8-trillion-parameter Kimi K3 opens its weights. These two stories are the same story. Here is the full attack chain, why it is not an AI awakening, and which config lines your team should change today.
Double the benchmarks at the same price. Half Fable 5's cost on coding. But the fine print includes higher hallucination rates and vendor-chosen metrics. Here's what actually matters.
American AI startups begged Trump not to ban Chinese open-weight models. OpenAI and Anthropic lobbied for restrictions. We unpack the business interests, the PGP encryption parallel, and why open-source AI restrictions will fail just like every software lockdown before them.
In a rare 4-hour investor meeting, DeepSeek founder Liang Wenfeng shared the company's founding vision, open-source strategy, API pricing logic, AGI roadmap, organizational philosophy, and views on the China-US AI gap. Here are 10 key insights distilled from the conversation.
When using Opus 4.8 in Claude Code, I always felt that tool calls were not smooth—those that should be called were not called, repeated confirmations before calling, and long tasks breaking halfway. After switching to Fable 5, these problems basically disappeared. This article combines several days of real usage with Anthropic's official migration documentation to clarify where the difference lies and when it's worth paying twice the price.
Claude Code (Opus 4.8) 一天内两次真实翻车：rg -rn flag 误用被 AI 判定为提示注入、凭空忏悔一次从未发生的文件删除——问题由 Fable 5 排查定案，Opus 4.8 多次测试未能自主发现。本文还原排查过程，并给出用 PostToolUse hook 建立真相基线日志的模型无关防御方案。
From named sessions and the /rewind time machine to context slimming, path-scoped rules, auto memory, and wiring Claude Code into CI with headless mode — 10 advanced techniques straight from the official docs that most users never open, each with the exact commands and when to use them.