Latest explainers
All →
Free
Deep Dive
№ 1556
DEEP DIVE
AI Is Everywhere. Why Hasn’t the ‘Agentic Organization’ Emerged Yet?
Eighty percent of companies have yet to see AI impact their bottom line. The issue is not just model capabilities, but that enterprises are still jamming agents into legacy processes: workflows, governance, leadership approaches, and talent development must all be rebuilt together.
09-17 · 12 min read
Free
洞察
🎧№ 1552
How LLM Inference Engines Actually Work: From a Single Token to Agent Caching
A single forward pass generates only one token. Grounded in this physical reality, understand Prefill, Decode, the KV Cache, Continuous Batching, PagedAttention, and why AI Agents rely so heavily on Prefix Caching.
▶ Play09-17 · 12 min read
Free
Deep Dive
№ 1549
DEEP DIVE
From "Supervisor" to "Orchestration System": A Hands-On Grok Bot Engineering Guide to Managing 200+ Coding Agents
A step-by-step guide to building the full loop: start with one domain Bot, delegate to Cloud Agents, validate Proof, patrol Notion, merge by risk tier, learn through Jenny, and respond to P0 incidents.
09-17 · 20 min read
Free
Deep Dive
🎧№ 1558
DEEP DIVE
Paul Graham: When Startups Make Decisions, Don't Just Ask How to Make More Money—Ask How to Make the Company More Powerful
How does a company evolve from a subservient tool or vendor into a critical node commanding customer relationships, network effects, and long-term optionality? This explainer unpacks Paul Graham’s playbook on startup power, while preserving its most vital constraint: every step must make the customer better off first.
▶ Play09-14 · 12 min read
Free
Deep Dive
№ 1555
DEEP DIVE
How to Design and Build a Custom Agent Harness for Your Business
True agent customization is not about chasing the strongest model, but engineering a harness tailored to your business task through minimal primitives and composable middleware.
09-14 · 8 min read
Free
Tutorials
№ 1554
PRACTICE
Hands-On Breakdown: How to Use GPT-6 Astra to Build a Large-Scale Space Exploration Web Game
Using Void Explorer as the main case study, this guide breaks down how to define gameplay and visual direction first, then build observable testing, multi-scale coordinates, streamed terrain, performance benchmarks, and a Blender asset pipeline.
09-14 · About 18 min read
Free
工具教程
№ 1553
How to Systematically Evaluate Agent Skills: A Complete Guide from Trigger Cases to Automated Scoring
When you revise a Skill, did it genuinely improve, or did it just look smoother in a few test runs? This hands-on OpenAI guide lays out a complete evaluation loop across six steps: define success, run manual trials, design positive and negative cases, inspect JSONL traces, and review quality with a structured rubric. The article preserves all code and includes an interactive tool that directly generates test prompts and checklists.
09-14 · 16 min read
Free
洞察
🎧№ 1557
Who Is Using AI to Change Software Development? AI Programming Is Giving Rise to a New Kind of Software Developer
They may not be familiar with code syntax, but they understand the business, can test, can spot errors, and can deliver software. What is really shifting is not the professional baseline, but the barrier to implementation.
▶ Play09-13 · 12 min read
Free
Deep Dive
№ 1550
DEEP DIVE
Using Grok Bot for Customer Support: A Hands-On Guide from Multi-Tool Connections and 5 High-Frequency Tasks to Automated Routines
From item-by-item authorization for Plain, Stripe, and Databricks SQL, to copy-ready instructions, deliverables acceptance, stop conditions, and Routine setups across five support workflows.
09-12 · 15 min read
Free
Deep Dive
№ 1548
DEEP DIVE
Grok Bot 101: How to Build Your Own Bot—and Four Real-World Workflows That Actually Deliver
What Grok Bot is, how to define a Bot with three fields, how to trigger tasks via chat, routines, and other Bots, and how to manage the permission risks of a shared computer.
09-12 · 10 min read
Free
Deep Dive
№ 1547
DEEP DIVE
Spring Cleaning for Agent Configs: A Practical Guide to Refactoring Skills and AGENTS.md for GPT-6 Astra
As models grow more capable, the repository rules once written to scaffold weaker predecessors are now actively holding them back. This guide turns OpenAI Developers' recommendations into four actionable refactors: narrowing skill descriptions, turning AGENTS.md from mandatory reading into an on-demand index, granting explicit authority in safe environments, and encoding definitions of done directly into task prompts—complete with verification checks for every step.
09-12 · 12 min read
Free
Deep Dive
🎧№ 1546
DEEP DIVE
T:0 Engineer: Why Do AI Accountants Always Guess? Because the General Ledger Only Records Conclusions, Discarding Context
A long-form essay by Erik, an engineer at T:0 (an Airwallex subsidiary): Hook up an agent however fast to the general ledger, and it can still only guess. Double-entry bookkeeping already comes with an arithmetically verifiable 'ontology.' Only by restoring the links software discarded can AI point to evidence and answer 'why.'
▶ Play09-12 · 17 min read
Free
Launch
№ 预览
LAUNCH
Cursor launches Projects, delegates tasks to thousands of subagents, and runs recurring work for months without prompting
Projects has its own computer in the cloud and preserves shared context across months; instruct it once, and it gets to work on Slack messages, PR changes, or schedules. Currently in beta, rolling out gradually to all users.
09-12 · 6 min
Free
Launch
№ 预览
LAUNCH
OpenAI Opens the GPT-Live-1 API: Bring GPT's Voice Conversation Capabilities into Any App at $0.05 per Minute
The full-duplex voice model first launched in ChatGPT is now open to developers. How it handles interruptions and noise, how it delegates tasks to the backend, and what to make of the benchmarks, pricing, and 10 demo videos.
09-12 · 21 min read
Free
洞察
№ 预览
Anthropic Releases Explosive Security Report: Discloses Range of AI Threat Campaigns, Naming Alibaba, DeepSeek, Moonshot AI, and Others for Distilling Claude
The report discloses misuse operations disrupted between December 2025 and August 2026 across seven domains—from autonomous cyberattacks, influence campaigns, and surveillance to weapons development and illicit distillation—naming Alibaba, Moonshot AI, DeepSeek, Zhipu, Xiaomi, SenseTime, and MiniMax for industrial-scale extraction of Claude's reasoning capabilities, based on Anthropic's unilateral allegations.
09-11 · Approx. 18 mins
Free
Launch
№ 预览
LAUNCH
OpenAI Launches Agents API: One Call to Run Codex-Grade Agents in the Cloud
OpenAI opens the harness and sandbox infrastructure that powers Codex into an API. How it works, what it can do, how it is priced, and what limitations exist.
09-11 · 20 min
Free
技术解读
№ 1545
iPhone Duo's Official Human Interface Guidelines: The Device Changes Form at a Gesture, but Your Attention and Workflow Never Break
Apple’s rules for its first foldable iPhone boil down to one core mandate: fold, unfold, or prop it up—no matter how the form changes, where the user is reading, where the cursor rests, and which step of a task they are on must never break.
09-10 · 18 min read
Free
洞察
🎧№ 1544
GrokBot Product Lead Retrospective: Building GrokBot in a Month, from a Chatbox to an ‘AI Colleague with Its Own Computer’
Roman Ugarte explains how GrokBot came to be: why the team started fresh instead of adding it to Cursor, why every Agent gets access to a cloud computer, and how a small team built a prototype in four weeks before using an internal beta, feature cuts, and reliability fixes to reach public launch.
▶ Play09-10 · 18 min read
📮 New explainers, straight to your inbox
Every new explainer, the moment it's out. Unsubscribe anytime.
📱Want it to feel like an app? Tap Share → Add to Home Screen for a full-screen read.
Add Best Blog to your Home ScreenFull-screen reading, one tap away
- Tap at the bottom
- Choose Share
- Choose Add to Home Screen
- Tap at the bottom
- Choose Add to Home Screen
- Tap at top right
- Scroll down, tap More
- Choose Add to Home Screen