资讯与观察
AI 行业动态、工程实践、产品方法和社区故事。
Show HN: ChemX – Architectural AST linter for LLM context bloat, AI slop
Chemical X replaces noisy compiler dumps, unstructured whole-file reads, and AI code smells with an index-first SQLite architecture. Built for Cursor, Claude Code, Cline, and terminal agents.
LATEST STORIES
最新内容
Show HN: Pagelapse – watch a web page's decade精选导读
Pagelapse pulls Internet Archive captures of any URL, keeps the ones where something meaningful changed, and lets you drag between the before and after of each change.
Prbot – an agent that fixes PR bugs and proves the fix in a Docker sandbox精选导读
A graph-based multi-agent system that reviews a pull request, writes a patch for the security and
Show HN: Gifup – GIF tools that run in the browser (ffmpeg.wasm)精选导读
Hi HN. GIFUP was an avatar and glitter generator I ran from 2007; it made about 1.3M animations before the web moved on. This year I rebuilt the domain as a set of GIF tools where the encoding happens in the tab via ffm…
Show HN: Sectr – Serverless backend platform for easy deployment of AI agents精选导读
Hey HN, I've been building Sectr, a backend-as-a-service for making it easy(ier) to develop and deploy AI agents. Deploying agents requires non-trivial systems design work. Consider a support agent: how do you stream me…
A topological model for provability logic精选导读
Gödel’s incompleteness theorem illustrated the need to distinguish between what is true and what is provable. There are true statements that cannot be proven.
Data Recovery CEO Indicted for Allegedly Scamming Ransomware Victims精选导读
A Florida man who was the subject of a 2019 investigation by ProPublica was indicted last month on federal charges that he defrauded clients of his ransomware data recovery firm.
Anthropic trained Claude on illegally obtained Stanford professors' books精选导读
AI giant Anthropic illegally scraped and pirated the work of over 10 Stanford professors to train its Claude models, a federal judge ruled in a May 2026 lawsuit.
TypeSafe AI发布Jev：一种只返回类型化概率而非文本的决策模型精选导读
前 OpenAI 研究员 Diogo Almeida 创立的旧金山 AI 实验室TypeSafe AI发布了Jev，这是其所谓的 System One Models 中的首款产品。Jev 不生成文本，而是返回带有类型的概率化决策，软件可以直接据此采取行动。
AI review optimized for recall (catches more defects than Codex or Claude)精选导读
A self-hosted AI code reviewer for GitHub pull requests: many narrow reviewers, one verified review.