小互
Best Blog
AI, Explained
Home
Explainers
Podcast
About
Member
Subscribe
中
EN
日
⚙ 后台
Sign in
☀️
Home
Explainers
Podcast
About
Member
Subscribe
中
EN
日
⚙ 后台管理
Sign in
✕
ACCOUNT
Sign in
Sign in
Register (free)
✓ Free accounts get bookmarks and cross-device reading progress
✓ Buy later and the membership attaches to this same account
Sign in with Google
or with email
Sign in
Email me a login link
Forgot password?
No account? Register free →
Have an access code? Redeem to sign in →
BUY
Buy
Yearly $49
Monthly $5.99
Single $1.99
Pick the article to unlock…
YC names the startup ideas it's eager to fund right now
Chroma founder's 12 rules for the AI-era company: teach AI the job first, hire only if it can't learn
VC Sarah Guo on AI startups: what to do when a giant could crush you overnight
Hugging Face and Cerebras make Gemma 4 voice chat feel human
Google engineer turns a year of harness engineering into 12 rules and a copy-paste playbook
Inside Anthropic: the harness wrapped around agents is coming apart
Cerebras details how it built a knowledge base that leaves data where it lives and lets AI fetch it
AI can copy your work in seconds — but not these eight things
The CTO is an AI too: how a nearly all-AI team shipped a product feature
How Should Websites Optimize in the AI Search Era? Google's Official SEO Guide
You just hired a million bad employees
How much did this order really make? Retail finance turns to AI
Anthropic's playbook for AI-native startups: four stages, graduation criteria, and ready-to-copy prompts
DoorDash's AI Shopping Assistant: It's Not the Model, It's the Tools and Memory
How Microsoft Ships AI Agents at Enterprise Scale: Breaking a Production Agent into 5 Layers
Ploy Switched Production AI from Opus 4.8 to GPT-5.6 Sol: Cutting Latency by Over Half and Costs by 27% Without Losing Quality
Low-Margin Industries Are AI's Biggest Winners
OpenAI Staff Reveal How They Really Use GPT-5.6: Unlimited Quota, Not Always Maxed Out
One AI Per Department Backfired — Sierra's Single Assistant Now Handles 70% of Its Code
OpenAI's Official Guide: 9 Copy-Ready Codex Prompt Workflows for Fixing Bugs, Turning Screenshots into Prototypes, and Cloud Refactors
Claude Code's Two Knobs, Explained: One for Capability, One for Effort
Anthropic's Playbook: Fable 5 Advises, Sonnet 5 Foots the Bill
Claude Fable 5 in Practice: 8 "Find the Unknown" Prompt Patterns, from Blind-Spot Scans to Post-Read Quizzes
Sakana AI Co-Founder: The Ability to Swap Models on Demand Is Itself a Deterrent
Working With Claude Fable 5: The Real Skill Is Finding Your Own Unknowns
As AI Gets Cheaper, Renting Generic Intelligence Gets Riskier
Every's Head of Consulting Can't Code — She Still Builds Her Own Work Systems With Codex
Anthropic's New AI Agent Architecture Guide: Ask 3 Questions Before Going Multi-Agent
未来的网站会为每个访客现场拼装：Adobe 演示按意图实时生成专属页面
The AI Leverage Ladder for PMs: Two Paths to Higher Output, Plus 3 Copy-Paste Prompts
Claude Fable 5's Official Prompting Guide: A Dozen Copy-Paste Fixes, From Over-Planning to Fake Progress Reports
Claude Code's Official Playbook: 4 Levels of Agent Loops to Unattended
AI Replaced 700 Agents at Klarna. Then Quality Dropped.
OpenAI President: The Best Product Is No Product
What Is Loop Engineering, Actually?
The Fourth Step Everyone Skips Is What Actually Makes AI Engineering Work
Databricks benchmarks AI coding agents on millions of lines of real code
Memories.ai's O-MARC makes audio-visual AI faster, cheaper, and more accurate
Study finds a sweet spot for AI-assisted writing — not too much, not too little
The model you picked through a router might be swapped — one random number proves it
A single wrapper pushes Opus 4.8 and Fable 5 to 99% on ARC-AGI-3
Meta AI's Proactive Memory Agent Teaches Models When Not to Remind You, Boosting Terminal-Bench Accuracy by 8.3 Points
Claude Cowork's Top Use Case Is Office Admin (33.4%), Not Coding (8.7%): Interface Shapes How AI Gets Used
What Does Each Brain Region Like to Watch? EPFL Evolved AI-Generated Videos to Find Out
Google Research Unveils SensorFM: Trained on a Trillion Minutes of Wearable Data, It Wins 33 of 35 Health Tasks
Gemma 4 Technical Report: How a Small Open Model Takes On Large Ones with Reasoning and Memory Efficiency
LangChain Tunes the Harness, Not the Model — Nemotron 3 Ultra Closes In on Opus 4.8 at 1/10 the Cost
AI Self-Improvement Starts Outside the Model: Lilian Weng on Harness Engineering
Liquid AI's Antidoom Fixes Reasoning Models' Doom Loops With a Single Token — Now Open-Sourced
NVIDIA Research Unveils HORIZON: Unattended Agents Push Full RTL Chip Design Benchmark to 100% Pass Rate
Anthropic Analyzed 400K Claude Code Sessions: Expertise Beats Coding Skill
Bridgewater Built a Financial-Filtering Model with 84.7% Accuracy — and Open-Sourced the Method
No Surgery Required: Meta's Non-Invasive Brain Reader Hits Nearly 8x the Accuracy
GPT-5.6 Sol's Cheating Rate Hits a Record High — Evaluators Say That's Reassuring
Wan Streamer: Real-Time AI That Listens, Watches, and Talks at Once
IBM Unveils World's First 0.7nm Chip, Packing Nearly 100 Billion Transistors on a Fingernail
Anthropic's six-step playbook for code migration: how Bun moved a million lines from Zig to Rust in two weeks
Google's gemma-trainer skill fine-tunes a custom Gemma right on your own machine
An 80k-Character Anti-Slop Design Law: Drop Slop.md Into Your Agent
Design Skills That Strip AI Taste From Frontend: Impeccable
Pay with Stripe
Have an access code? Redeem →
← Back to membership benefits