Code4Func @Code4Func

Just launched Loop Library - a curated list of agent loops you can use right now. Find loops, submit your own, tokenmaxx!! signals.forwardfuture.ai/loop-library/

This video on how to review AI-generated code by @owainlewis is a masterpiece. His 4-layer approach: 1. Automate the obvious (hooks, linting, tests) 2. Review locally (AI reviewing AI) 3. Automated CI checks 4. Human review Layers 1-3 are tooling. Set them up once, and they run on every PR. Layer 4 is the one that decides whether you ship a breach. And it's the layer nobody actually teaches. So I wrote the manual for it. 9 things a human has to check that no linter, CI gate, or AI reviewer will catch for you:

Mari @Tech_girlll

2 days ago

x.com/i/article/2067…

17 36 190 46K 393

Best accounts to follow from each frontier lab to stay constantly up to date Anthropic @karpathy - must-follow account for AI; recently joined Anthropic @bcherny - Claude Code creator, always shares great tips @trq212 - also a Claude Code developer; writes amazing articles on CC OpenAI @polynoamial - works on reasoning research, shares a lot of technical details @gabriel1 - Sora developer, great career path @jxnlco - works on dev experience, shares a lot about Codex Google AI @OfficialLoganK - all the major Google Gemini and AI Studio updates @ammaar - product and design; shares great things about vibe-coding in Google AI Studio @fofrAI - cool use cases for generative models Cursor @leerob - the loudest voice behind Cursor updates @ericzakariasson - shares great insights on using Cursor @mntruell - Cursor’s CEO; major releases and usage updates xAI @milichab - recently joined xAI, shares updates on Grok @skcd42 - also covers major Grok releases @ai_explorer25 - covers all ai content and free resources

keyboard_arrow_left Previous keyboard_arrow_right Next

// Automating SKILL.md Generation // Increasingly, mining sessions is one of the best ways to improve your agents. OpenAI released something similar yesterday that lets Codex package skills from interactions. (bookmark it) This paper explains a related approach. They run a three-stage pipeline that segments GUI trajectories, clusters them into candidate skills, and trains a skill-aware policy. The clusters are genuinely readable, with five of eight hitting 0.95 or higher purity against ground-truth workflow labels. But readability does not transfer. GRPO lifts skill-step accuracy only from 18.5% to 20.5%, leaves BrowseComp+ flat, and loses to trivial frequency priors. The authors name the three culprits: a weak boundary detector, an orderless segment representation, and an offline reward model. Paper: arxiv.org/abs/2606.20363 Learn to build effective AI agents in our academy: academy.dair.ai

x.com/i/article/2067…

x.com/i/article/2065…

x.com/i/article/2066…

Excited to speak at the @aiDotEngineer World's Fair in SF! I'm expanding on this post: - Build a software factory to go from a taskboard -> agents shipping work - Let agents self-improve skills over time using loops - Manage hundreds of jobs while minimizing human bottlenecks

Zach Lloyd @zachlloydtweets

5 days ago

x.com/i/article/2066…

29 208 1K 251K 4K

x.com/i/article/2067…

This is EVERYTHING you need to know about building a Company Brain in 28min. From connecting all your tools into one intelligence layer to the new org chart around it. This is the new way to work in the AI era. Here's the full breakdown: 00:00 Introduction & AI Adoption 01:45 The Four Levels of AI Maturity 02:30 The Single Brain Concept 05:30 Building an AI-Powered Org 07:20 Specialist Agents & Agent Fleets 11:20 Workflows & Closed Loops 14:30 Real Agent Examples in Slack 18:00 AI ROI & Token Economics 20:45 Business-to-Agent Commerce 24:10 Action Steps & Future of Work

ericosiu @ericosiu

3 weeks ago

x.com/i/article/2056…

25 105 878 844K 3K

Loop Engineering 精华文章汇总! 2026 年 Agent 开始聚焦在长任务后，重点慢慢变成了： 如何设计一个能够持续思考、执行、观察、验证和演进的循环系统？ 从 Codex 到 Claude Code，从 OpenHands 到各种 Coding Agent。 业余项目和生产级系统之间最大的差距是Harness 工程，包括 Loop。 Agent 能不能持续工作几十分钟甚至几个小时？ 能不能在失败后恢复？ 能不能控制成本？ 能不能知道什么时候停下来？ 这些问题，最终都落到了 Loop 设计上。 📚 推荐阅读 1. Loop Engineering — Addy Osmani addyosmani.com/blog/loop-engi… 2. Loop Engineering — Firecrawl firecrawl.dev/blog/loop-engi… 3. What Is the AI Agent Loop? — Oracle blogs.oracle.com/developers/wha… 4. Harness Engineering — OpenAI openai.com/index/harness-… 5. Harness Engineering for Coding Agent Users — Martin Fowler martinfowler.com/articles/harne… 6. Agentic Loops: From ReAct to Loop Engineering datasciencedojo.com/blog/agentic-l… 7. Loop Engineering for AI Agents (Memory-First) — Mem0 mem0.ai/blog/loop-engi… 📄 推荐论文 1. Agentic Harness Engineering arxiv.org/abs/2604.25850 2. From Agent Loops to Structured Graphs arxiv.org/abs/2604.11378 🛠 推荐研究的开源项目 Codex CLI github.com/openai/codex OpenHands github.com/All-Hands-AI/O… PydanticAI github.com/pydantic/pydan… OpenAI Agents SDK github.com/openai/openai-… 重点研究： Loop 如何运行 Loop 如何停止 Loop 如何验证 Loop 如何恢复 Loop 如何调试 Prompt 决定 Agent 如何开始。 Context 决定 Agent 能看到什么。 Loop 决定 Agent 最终能走多远。 Loop Engineering： Think ↓ Act ↓ Observe ↓ Verify ↓ Evolve ↓ Repeat 你设计循环。 Agent 在循环中持续改进。 每完成一次循环，系统都会比上一次更接近目标。 Agent 从来不缺 Loop。 缺的是 Loop 的工程学。

The AI-native business has 3 things. Agents. Loops. Workflows. We're about to see a massive shift in this direction over the next few years.

ericosiu @ericosiu

6 days ago

x.com/i/article/2065…

7 36 323 98K 975

x.com/i/article/2066…

Step-by-step notebooks for building RAG systems github.com/langchain-ai/r…

x.com/i/article/2065…

Boris Cherny: "Overnight sub-agents do deeper work" 10-step Fable 5 setup you can copy this week: 1. Write CLAUDE.md - stack - commands - code style - forbidden files - review rules 2. Add PROJECT_MEMORY.md - verified facts - failed attempts - last session - next run 3. Create 1 Skill per repeated workflow - CI triage - PR review - design QA - deploy check 4. Add eval cases Put them in: eval/.jsonl 5. Split maker and verifier Maker writes the chang Verifier runs the app, tests, screenshots, logs 6. Use worktrees for parallel runs No shared checkout No file collisions No mystery edits 7. Send work by price Fable 5 plans across days Sonnet 4.6 does bulk edits Haiku 4.5 grades Opus 4.8 handles fallback cases 8. Put UI work behind screenshots If the task is visual, text logs aren't enough 9. Move long jobs to Routines CI failed? Run triage PR opened? Run review 7am? Send digest 10. End every run by writing the lesson back A fix that stays in chat dies there The rule: > Builder makes the change > Verifier checks the real artifact > Memory keeps the receipt > You read the diff Skip the verifier and you don't have an agent system You have a very confident intern with shell access

Codez @0xCodez

a week ago

x.com/i/article/2065…

33 139 1K 1.2M 3K

This looks accurate 😂😀

x.com/i/article/2064…

Most LLM features are easy to demo and much harder to operate. AI Governance is useful because it maps the topic to engineering work you actually have to operate. The book covers: • Route model requests and control cost • Deploy and scale beyond a demo • Build more reliable generative AI applications • In AI Governance, you’ll learn how to: Match the right safeguards to your… The production angle is the part I would pay attention to. The demo is the easy part. The useful engineering work is making the system reliable once it touches real workflows. Good fit for engineers building real AI systems and wanting a stronger mental model than another clean demo. Link in the first comment.

🔗 GitHub: github.com/tjboudreaux/cc… --- ✉️ If you’re into AI, ML, agents, and building real systems, join my newsletter (it’s free): dankornas.substack.com