资讯与观察
AI 行业动态、工程实践、产品方法和社区故事。
Grok Build vs. Claude Code: I tested which one has the better memory
On September 16, xAI announced memory in Grok Build, its terminal coding agent. The pitch was that Grok “keeps notes
TypeSafe launched Jev because sequential LLMs are “totally useless for computers”
When TypeSafe emerged last week after two years in stealth, backed by $40 million in seed funding led by DCVC,
17 分钟 · The New Stack
Your AI agent is burning tokens on choices that don’t need words
AI agents spend a ridiculous amount of compute generating text nobody actually needs. The decisions an agent makes along the
14 分钟 · The New StackLATEST STORIES
最新内容
Grok 4.7 was built to work for hours. It still fails most of the time.精选导读
A coding agent running for hours can make dozens of decisions as it edits files, runs tests, and works through
AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex精选导读
Amazon Web Services (AWS) is lifting the lid on a new open source, general-purpose AI agent, designed to give developers
AWS Weekly Roundup: AWS Builder Center mobile apps, Amazon Connect Talent GA, Amazon Corretto 27, and more (September 21, 2026)精选导读
Living in the Netherlands, I spend a fair amount of time on trains, and that is usually where I catch up on what the builder community is writing. Until now, that meant opening a laptop or squinting at a browser tab on …
Python Workers are now generally available精选导读
Python Workers allow developers to run Python web frameworks and AI orchestration libraries natively in the Cloudflare Workers runtime. You can seamlessly integrate with Cloudflare's ecosystem including D1, R2, and Work…
Your AI agent failed. The model might not be the problem.精选导读
As AI agents move into production, the path between a request and its result is becoming less predictable. An agent
One engineer shipped 2,000 PRs a month to production. Verification is the key.精选导读
Lauren Tan, an engineer on the Grok team at SpaceXAI, who previously worked at Cursor and Meta, recently published a
“Dormant deployments were quietly consuming storage”: Why Vercel tightened its free-tier rules精选导读
Vercel announced this week that teams on its free Hobby plan will now have older, unprotected deployments deleted immediately if
This week’s news from Zed, Anthropic, and OpenRouter shows why better harnesses matter more than better models精选导读
Our five most-read stories this week covered code collaboration, a model router, a UI change, a benchmark, and a caching
Claude couldn’t hack OpenAI. Then Anthropic shipped Opus 5.精选导读
Three security researchers at Hacktron AI found a memory-corruption bug in a widely used image library. Finding it was the