Mircea Trifan

Software Engineer @ Mgestyk | PhD Student @ uOttawa
Researching Diagram-as-Code & Code-as-Diagrams for LLM-driven systems
#AI #LLMs #NLP #DevTools #Web

[Leanpub @leanpub]

Be a Learning Machine by Alberto Souza is the featured book on the Leanpub homepage! @alberto_souza #Education #PersonalTransformation #books #ebooks

You’ll just need the Five Essential Elements of Learning

Through five essential elements, you’ll gain the ability to learn anything deeply—no matter how complex the subject.

These five pillars of effective learning will become lifelong tools, guiding you every time you set out to truly master new knowledge and retain it permanently.

If you're ready to stop passively consuming information and start truly mastering it, this book is for you.

Find it on Leanpub!

About the Book

Unlock Your Full Learning Potential with a Proven, Actionable Method

This book isn’t just about learning—it’s about mastering the art of learning efficiently and effectively. Whether you want to deepen your expertise or acquire new skills, you'll discover a powerful, structured approach designed to help you retain knowledge and apply it with confidence.

Inside, you’ll find practical, real-world examples of creating personalized learning plans, with a focus on software engineering—though the principles apply to any field. Unlike traditional learning guides that discuss theory without application, this book delivers clear, actionable steps you can implement immediately.

Inspired by athletic training and grounded in four key psychology theories, the author presents a dynamic method built around five essential elements. This framework empowers you to systematically absorb and apply knowledge, turning learning into a skill you can refine for life.

[Dr. Ganapathi Pulipaka 🇺🇸 @gp_pulipaka]

Great Python Programming! Finite Element Method with Python: An Essential Course with AI Enhanced Approaches! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Mathematics #Programming #Books #Coding #100DaysofCode
https://t.co/LKeXRojpp8

[Charly Wargnier ♨️ @DataChaz]

STANFORD JUST RELEASED A FREE COURSE ON ONE OF THE MOST CRITICAL SKILLS IN AI RIGHT NOW: BUILDING SELF-IMPROVING AGENTS.

The entire curriculum is focused on self-correction. It skips the basic API wrappers and gets straight into the mechanics of frontier reasoning.

If you want to understand how autonomous systems actually learn from their actions, the syllabus covers the exact stack being used today:
→ Test-time compute and verifiers
→ Constitutional AI and RL
→ Planning, memory, and tool execution
→ Architectures for deep research agents

It is highly project-based.

You watch the lectures, build alongside the researchers teaching them, and walk away with a functional self-improving architecture.

I've put the full playlist in the 🧵↓

[Simon Brown @simonbrown]

I've had my copies for a few weeks now, and it looks like orders are being shipped with more regularity now. 🎉

I hope you find the book useful!

[rari🈀 @0xwhrrari]

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems

In this 15-minute workshop, he shows exactly how to build one from scratch

AI → Agents → Harness → Loops → Graphs

step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing

step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token

step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log

step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over

step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter

Anthropic calls this "dreaming"

Most people spend weeks building this by hand

You don't have to

Bookmark and watch it

Then read the full harness engineering guide below ↓

[Mihail Eric @mihail_eric]

I’m excited to finally announce the newest edition my Stanford course 𝗧𝗵𝗲 𝗠𝗼𝗱𝗲𝗿𝗻 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿. It has been 9 months in the making.

Last November, with the release of Claude Opus 4.5, coding agents experienced a step function improvement in capability. We all felt it. The LLMs were more powerful, could reason for longer, solve harder tasks.

This year’s iteration of my course reflects the 2026 metamorphosis of software engineering.

My core belief is simple: AI-native developers of the LLM era are going to become the most important members of any software organization. I have designed my course to train this next generation of engineers.

𝗪𝗵𝗮𝘁’𝘀 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝘁𝗵𝗶𝘀 𝘁𝗶𝗺𝗲 𝗮𝗿𝗼𝘂𝗻𝗱

First, 85% of my Fall 2025 class material is being thrown out. The Fall 2026 syllabus reflects the core capabilities AI-native engineers must have: agent skills, advanced context engineering, MCP portals, agent-ready codebase principles, agentic code review, security, parallelizing background agents, software factories, and more.

Second, I am going to teach my students how to have software taste. Every student will be required to ship pull requests to production-grade, real-world codebases. The course is collaborating with the top open-source AI repos who will offer support and mentorship to students on how to meaningfully contribute to their projects.

This has never been done before in any university course so I am incredibly grateful to our OSS Partners: @browserbase, @HeyGen, @CopilotKit, @semgrep, @OpenHandsDev, @milvusio, @marimo_io, Pi, @crewAIInc, @warpdotdev, @vercel, @cmux, @arizeai, @UnslothAI, and @anyscalecompute.

𝗪𝗵𝗮𝘁’𝘀 𝘀𝘁𝗮𝘆𝗶𝗻𝗴 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲

I’m fortunate to again have AI software engineering leaders and founders as guest speakers to share their learnings from building top coding agent products. Thank you to @leerob from @cursor_ai, @bcherny of @claudeai code, @EnoReyes of @FactoryAI, @silasalberti of @cognition, @0xine of @semgrep, Rajesh Bhatia of @Cloudflare , @amasad of @Replit, and @eladgil.

All resources will be available online. All classes will be available to the public.

9/22 on Stanford campus. See you in class. 

https://t.co/wTokHyUMsz

[Lunar @LunarResearcher]

Andrew Ng just released a free 2-hour course on building agentic skills from scratch with Anthropic:

0% → 00:15 - build your first agent skills with Claude
30% → 22:32 - work with Claude's pre-built skills
55% → 41:07 - learn skills vs tools, MCP, and sub-agents
100% → 01:06:06 - create skills for long-running agents

This 2-hour course can replace 10 paid courses on agent building

Taught together with Anthropic engineers

Bookmark it and watch tonight

Then read the full guide below ↓

[Andrew Ng @AndrewYNg]

How have software engineering fundamentals changed with agentic coding? Here is our AI Engineering Skills map for software engineering fundamentals. https://t.co/cnRLj43DLs

[Mircea Trifan @mobilepixel]

BMAD, Spec Kit, OpenSpec, Kiro: A Field Guide to Getting Real Work Out of AI Coding Agents by @roanbrasil https://t.co/Pt2hUvBqbV

[Mircea Trifan @mobilepixel]

OpenAI Computer History by Rick Hightower https://t.co/OPnwF8wK6M

[Mircea Trifan @mobilepixel]

Stanford Just Put an $850K/Year Skill on YouTube by @DareToBe_Better https://t.co/FDrpreqaRH

[Mircea Trifan @mobilepixel]

Anthropic Just Launched Claude Academy (And I Earned My 5 Badges) by @joenjenga_ https://t.co/yaQFxflcSo

[Mircea Trifan @mobilepixel]

WebMCP (Web Model Context Protocol): Agents are learning to browse better by @abvijaykumar https://t.co/hcM6NdkzJQ

[codila @0xCodila]

Andrew Ng just released 2-hour course on 100% Graph engineering: 1 prompt → 100 agents → loops → graphs from scratch:

10% → 9:14 - build your first agent from scratch
30% → 33:11 - Loop engineering
55% → 1:02:46 - Graph engineering
75% → 1:30:15 - agents that rewrite themselves
100% → 1:49:05 - full graph system that work without you

most graph tutorials stop at the diagram - this one has you running one in the first 20 minutes

watch this brilliant course, build the graph - then read the full architecture below ↓

[Kirk Borne @KirkDBorne]

The Mathematics of Large Language Models — A Readable Guide to LLMs, Transformers, Diffusion, Neural Networks, and Generative AI: https://t.co/3sDIaIroX8

[Roan @RohOnChain]

Don't waste 2 years learning to code.

Thariq Shihipar, the Anthropic engineer who built Claude Code tells you what to learn instead.

1 hour course. Free:

00:00 - build AI agent with loops
40:47 - prompting Claude with HTML
1:15:07 - Anthropic's coding playbook

Writing code is the old job. Building AI agent loops is the new one.

Bookmark now & read the article below to build your own AI agent with loops & graphs.

[codila @0xCodila]

Creator of Claude Code just dropped a free masterclass on agent engineering with Opus 5 from 0% to 100%:

“80% of our engineers are using self-improving loops”

10% → 3:38 - why they deleted 80% of the system prompt
30% →6:55 - delete your CLAUDE.md every 6 months
55% →17:44 - one prompt, 11 days, entire codebase rewritten
80% → 21:59 - the prompt that's been running for 15 days
100% →25:27 - two promts that spawn 1,000 agents

most people are still writing longer prompts - he's deleting them and running 1,000 agents instead

bookmark & watch - then read the full agent orchestration playbook below ↓

[Karun Singh @karun1710]

We're hiring a Research Engineer at @Arsenal ⚽🔴⚪ to work directly with our Men's First Team!

We're building state-of-the-art AI models for the football domain. This role will focus on building the application layer for our research to advance coaching and analysis workflows.

[Codez @0xCodez]

IBM just released a 1-hour course on building agentic knowledge graphs from scratch:

• 00:00 - Introduction to knowledge graphs
• 05:35 - Building your first agentic graph
• 19:59 - Agentic memory powered by graphs
• 30:39 - Graphs for multi-agent orchestration

This 1-hour watch will replace 10 paid courses on agentic engineering.

Watch it today, then learn how to become a knowledge graph engineer in the article below.

[vartekx @vartekxx]

Boris Cherny just dropped 7-page PDF on Graph Engineering - how 4 Claude prompts replace 4 trained ML models

The twist: your agent's memory dies with the context window. A knowledge graph makes it permanent - and now you build one with prompts, not ML engineers.

here's 4 prompts, step by step:

prompt 1 → extraction - Haiku pulls entities + relations - one call per doc - no NER, no labeled data

prompt 2 → resolution - Sonnet merges duplicates string matching will never catch - two different names, same person

prompt 3 → summarization - Sonnet builds profiles from multiple sources - facts that never appeared in the same document

prompt 4 → querying - feed the graph to Sonnet - every answer cites a specific edge - no hallucination

how to wire this into agents today:

step 1 → shared memory for multi-agent teams - workers read/write one graph - orchestrator's context stays clean

step 2 → grounding layer for eval loops - evaluator checks facts against graph edges, not vibes

the result: one Pydantic schema replaces weeks of ML training per domain - precision 1.00 - 10k docs cost under $10

this 7-page PDF is what comes after loop engineering

bookmark this, then read the article below ↓