#Engineer

Anthropic engineer: “Anthropic hired me at $350K–$950K because I know how to build harnesses. 99% of people still hand-roll multi-agent systems and wonder why they break. I build systems that run loops + sandbox tools + turn yesterday’s logs into new skills — same model, 10x more reliable agents that keep improving overnight.” Opus 5.5 → Agents → Harness → Loops → Graphs In a short workshop, he shows exactly how to build one from scratch. step 1 → harness handles loops, context, and sandboxing step 2 → brain and hands separated — 60% faster to first token step 3 → runs server-side, resumes from the log after crashes step 4 → failure is cheap — retry and replay instead of starting over step 5 → yesterday’s logs become new memory — the system 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 Opus 5.5 harness engineering guide below ↓

Stop letting unfinished Opus 5.5 runs eat your budget Set up the harness before your next long task Save progress, verify results, reuse the workflow The full 7-layer setup below ↓

Anthropic CEO Answers the Question Everyone Cares About Most: Should You Still Learn Programming Now? 1. Programming will be the first to be eliminated. AI is already writing code, debugging errors, and building applications. The shift toward automating entire software engineering workflows is already underway. Learning to code just to secure your job may no longer be enough. 2. Even if you only do 5% of the work, it still has value. AI handles 95% of the work, and you handle the remaining 5%. Your productivity could increase dramatically. Knowing how to direct AI and make the right decisions is becoming more valuable than doing everything yourself. 3. The most promising careers are human-centered. Careers that combine human interaction, real-world expertise, and analytical thinking could have an advantage. Healthcare, robotics, and other fields that require judgment and human understanding are worth watching. 4. Critical thinking may be the most important skill in the next decade. AI can generate convincing answers, but convincing doesn't always mean correct. The ability to question information, verify facts, and make independent decisions will become increasingly valuable. 5. If you don't use AI well, it will make you dumber. Relying on AI for every answer without understanding the reasoning can weaken your ability to solve problems independently. The goal isn't just to get work done faster. It's to use AI while continuing to build your own skills. 6. He's bullish on semiconductors as capitalism's victory in the next decade. AI needs physical infrastructure to scale. Chips, computing power, energy, and advanced manufacturing could create major opportunities. The next wave of AI growth won't be limited to software.

Elon Musk gave incredible advice on how engineers can turn their ideas into real companies, and why the fear of failure shouldn't stop anyone from trying “If you study engineering and you figure out how to design new things, then it's relatively easy to start a company” Find like-minded people, build a compelling prototype as quickly as possible, and get the funding needed to bring your idea to life And if it doesn't work the first time, try again “You're not going to starve to death. What's the worst that could go wrong?”

Learn Python. ⠀ Learn JavaScript. ⠀ Learn React. ⠀ Learn Docker. ⠀ Learn AWS. ⠀ Learn Kubernetes. ⠀ Finally, you start feeling confident. ⠀ Then someone says, “I built the whole app with a prompt.” ⠀ Welcome to being a developer. ⠀ After 16+ years in engineering, I understand why this feels exhausting. Every time you get comfortable, the industry gives you more homework. ⠀ But I’d redraw the last part of this curve. ⠀ Your engineering knowledge still matters when you have to explain why: ⠀ • The app works locally but fails in production. ⠀ • One database query takes down the API. ⠀ • A retry charges the customer twice. ⠀ • An AI-generated endpoint lets users access someone else’s data. ⠀ Knowing how to investigate those problems takes experience. Every layer you learned gives you somewhere to start. ⠀ That knowledge helps while you’re prompting, too. ⠀ You can spot a missing requirement, question a design choice, and catch a dangerous assumption before it spreads across twenty files. ⠀ I want AI to handle more of the repetitive work. I also want to understand what I’m putting into production. ⠀ If you’re feeling behind, try this: ⠀ Take one small feature you already know how to build. Ask an AI coding tool to implement it. Then review the result like a teammate’s pull request. ⠀ 1. Read the diff. ⠀ 2. Check the dependencies. ⠀ 3. Test the failure cases. ⠀ 4. Find something you would change and explain why. ⠀ You’ll learn the tool while exercising the judgment you’ve spent years developing. ⠀ And if you’re just starting, follow the generated code all the way through: from the button, to the API, to the database, and back. ⠀ You don’t have to restart your career every time the tools change. ⠀ You do have to keep learning. That part of the picture has always been accurate. ⠀ Which skill on this chart took you the longest to learn?

This is f*cking insane. Nvidia founder and CEO Jensen Huang: "Nobody writes prompts anymore. The new job is building loops and graphs The engineers who stopped prompting are already years ahead, and the rest will end up working for them" In this 50-minute talk, Jensen explains why prompting is over and what the best engineers are building instead Prompts → Agents → Loops → Graphs → AI Workforce Using AI doesn't mean writing better prompts into a chatbot It means loops that do the work, and graphs that run the loops without you 95% of people are still polishing prompts, the 5% who build loops and graphs will run everything Worth more than any $2,000 AI course Bookmark and watch it today Then save the full harness engineering guide below before everyone catches up ↓

Anthropic engineer: “95% of our engineers are using self-improving harnesses + Opus 5.5. Now everyone is building agentic systems around them.” In 1–2 months, we’ll all be building harnesses to orchestrate self-improving agents. No more raw prompting. In a 35-minute lecture, Anthropic engineer shows how to build a self-improving agent harness from scratch with Opus 5.5. Worth more than a $1500 agentic course. Watch it Then read the full Opus 5.5 harness engineering guide below ↓

Tech roles tier list: S Tier: Account Executive, Head of Sales, Penetration Tester A Tier: Data Scientist, Cobol Developer B Tier: Product Manager, Solutions Engineer, Member of Technical Staff C Tier: Engineering Manager, SDET F Tier: VC, Scrum Master, Agile Coach

LEARN an Engineering Software... If you're in Mechanical Engineering, learn AutoCAD, SolidWorks, MATLAB and ANSYS. In Chemical Engineering, learn Aspen HYSYS, Aspen Plus and MATLAB. In Civil Engineering, learn AutoCAD Civil 3D, Revit, and ETABS. In Electrical Engineering, learn MATLAB/Simulink, ETAP, AutoCAD Electrical and PLC programming software. In Petroleum Engineering, learn PETREL, Eclipse, PROSPER and PIPESIM. In Mechatronics Engineering, learn MATLAB/Simulink, SolidWorks, LabVIEW and TIA Portal. In Agricultural Engineering, learn AutoCAD, SolidWorks, MATLAB and ArcGIS. In Computer Engineering, learn Python, MATLAB, Proteus and Multisim. In Structural Engineering, learn ETABS, SAFE, and Tekla Structures. In Environmental Engineering, learn ArcGIS, EPANET, SWMM and MATLAB. Learn at least one engineering software before you graduate.

Why did racing cars start bouncing down the straights? Using MATLAB Agentic Toolkit, this visual helps students explore the physics of porpoising. Lower ride height creates more downforce. Too low, and airflow can detach, reducing downforce and allowing the car to rise again.

a16z's Erin Price-Wright says factory technicians can now retool production lines with AI in 20 minutes, a job that used to take an outside integrator 3 months: "Historically, if you're setting up a line with a lot of automation, you really need to be producing a lot of one single thing. That's how you get the cost down, and how you justify investing in a pretty bespoke manufacturing line." "But what we're seeing across our portfolio is that manufacturing technicians themselves have the intuition, and now the software tools, to change the economics of producing low-volume, high-mix on the line." "A manufacturing technician, not necessarily someone with a college degree or who's studied software engineering, can now use these tools to reprogram and reconfigure their lines on the fly, because they understand the manufacturing process." "Instead of calling a systems integrator, which takes 3 months and hundreds of thousands of dollars to reconfigure a line, you can have a manufacturing engineer use Claude and do that in 20 minutes. That's been a real game changer." @espricewright

The American Dynamism 50 is a16z's annual list of companies building for America's future. This year's edition covers the industrial base end to end, from the inputs that come out of the ground to factories that make things and systems that deter conflict. a16z's Erin Price-Wright and Connor Love join Elena Burger to break down this year's list and its theme, Production is Deterrence, built around a simple idea: "You don't have a defense industrial base without an industrial base." 0:50 From mines to factories and systems 3:05 How the internet and nuclear was built 5:05 Drones built DJI into a robotics giant 6:50 Defense dollars pay for new factories 8:30 SpaceX and Tesla lessons on scale 10:15 How Mariana runs a mine on software 12:20 "AI cannot turn a wrench yet" 14:10 Retooling in 20 mins, not 3 months 17:45 Startups build before Pentagon asks 20:35 Why hard tech can be more valuable 24:45 The race for the biggest American flag 28:25 How defense parts unlock US robotics 32:05 The rise of the "manufacturing middle" 37:25 Anduril and SpaceX founder mafias 41:05 Private capital: USA's edge over China 46:30 The buildout must hit Middle America YouTube: @espricewright @ConnorLoveCA @VirtualElena

CLOUD + DEVOPS + AUTOMATION = GOD-LEVEL ENGINEERING 🚀 Save Now, this 45 days Learning Visuals

Generative AI systems can create content, like text or code, based on data they've been trained on. And in this bootcamp, @andrewbrown (and many other instructors) teach you key GenAI concepts. You'll get hands-on experience with Python data libraries, learn about prompt engineering, model fine-tuning, and AI agents, and lots more.

00:15 - The right way to prompt Claude 33:21—What makes Claude act dumber in your code 01:33:39 - How Anthropic uses Claude every day 02:50:56 - A fix that makes Claude way smarter - This The 4-hour Anthropic free course replaces about 10 paid engineering courses. Watch it today, then bookmark it for later.

Anthropic senior engineer: “Prompting is no longer the job. 99% of people still open one chat and call it agents. I run agents inside /loops + /graphs + /harness — same model, same tokens, 10x more completed work. The system plans, verifies, and keeps shipping while I’m offline.” Prompts → Agents → Loops → Graphs → Harness In this 1-hour course she shows exactly how Anthropic builds a team of self-improving agents that recover and improve without you. Worth more than every $1500 agent engineering course combined. Watch it today before it gets buried. Then read the full guide for Opus 5.5 loop + jev engineering ↓

Your Claude loops can burn money while nothing changes Use Jev to filter tasks and cut decision costs Fix the trigger before another overnight run The full Loop engineering + Jev engineering setup below ↓

holy f*ck, this one page turns Obsidian + Opus 5.5 + Jev into a Karpathy-grade second brain that thinks with you 24/7 built on Karpathy's second brain stack and classic Zettelkasten the loop: > Jev reads every note in your Obsidian vault before Opus 5.5 touches it > Opus 5.5 writes only the lines worth keeping > every note links itself into the Zettelkasten graph on save > the vault keeps thinking after you close the laptop the result: > 80% less of your week inside chat windows > hours back for the work you actually get paid for > a Karpathy-style vault that gets sharper with every note the stack: 📁 Obsidian - the vault itself ↳ 📁 Claude Opus 5.5 - the writer ↳ 📁 Jev - the reader that decides what matters ↳ 📁 obsidian-skills - teaches Claude your vault's formats ↳ 📁 claudesidian - a ready Claude Code starter vault, organized with PARA ↳ whoever wires Obsidian, Jev and loop engineering into one second brain first is who the next promotion lands on

THIS IS AN ABSOLUTE GOLDMINE  The team at Anthropic just revealed one of the most effective techniques for Claude Code The core concept: run Sonnet, Haiku 5.5, and Opus 5.5 simultaneously, letting each model focus strictly on what it does best You get higher quality output while dramatically reducing token consumption, since every specific job gets routed to the optimal model To spin up Claude Code with this setup, simply execute:  ⁠claude --model sonnet --advisor opus⁠  Here is how the workload is split:  > Sonnet 5.5 handles the primary session, writes code, and applies bug fixes > Haiku 5.5 scans the codebase in parallel: performing searches, running grep queries, exploring docs, and auditing diffs > Opus 5.5 acts as an on-demand advisor for critical decisions and approves final code diffs > You stop burning expensive Opus context on routine tasks that don't require high-level reasoning Opus intervenes exclusively during three specific scenarios:  > Right before locking in an execution plan > Whenever the exact same error triggers twice in a row > Prior to marking a task as complete Sonnet builds. Haiku scans and explores. Opus reviews JEV engineering applies the exact same principle one layer deeper: routine execution forks that don't need high-level reasoning (determining which file to inspect, which tool to trigger, or whether to retry or stop) are processed by JEV in sub-milliseconds, leaving big models to handle only complex decision splits The full architectural tree: Sonnet 5.5 manages the primary session and modifies code Search maps out the repository structure via Haiku 5.5 Grep locates call references using Haiku 5.5 Docs fetches API specifications through Haiku 5.5 Opus 5.5 serves as an advisor, reading the complete conversation history whenever consulted JEV routes lightning-fast micro-forks in milliseconds Feed this tree structure alongside the prompt below into Claude Code Reconfigure my Claude Code workspace based on this architecture: 1. Run the primary session utilizing Sonnet 5.5, with Opus 5.5 designated as the advisor 2. Set up three read-only Haiku 5.5 subagents: search (maps out the repo), grep (locates call sites), and docs (retrieves API documentation) 3. Insert a single rule into CLAUDE.md: consult the advisor prior to committing to a plan, after encountering an identical error twice, and before marking a task as done 4. Direct rapid, deterministic decisions (tool selections, file paths, retries) through JEV. Show all modifications as a diff first. Do not execute any edits until I grant permission Bookmark this setup: it will become a daily driver in your workflow

🚨 Anthropic Enginner just dropped a FREE 27-minute workshop on how to actually write better prompts for Claude. Taught by the people who BUILT Claude. No registration. No paywall. No $300 course. And the first 8 minutes alone might teach you more than most paid prompt engineering courses. 🎯 Learn from the source, not the gurus. 🔗 Watch the session 👇

New in Claude for Legal: a gallery of ready-made artifacts for contract review, regulatory horizon scans, cite checks, and more. Start from the built-in example, add your own documents and connectors, and share it with anyone across the business.

✅ Claude Code ✅ Claude Cowork ✅ Claude Design ✅ Claude Finance ✅ Claude Science ✅ Claude Teacher ✅ Claude Legal ⬜ Claude HR ⬜ Claude Analytics ⬜ Claude Marketing ⬜ Claude Sales ⬜ Claude R&D ⬜ Claude Procurement ⬜ Claude Accounting ⬜ Claude Engineering

The @github engineering team built a best-in-class, truly multi-model harness, which we've implemented across Microsoft products. Introducing Microsoft Copilot harness in Foundry Agent Service, a simpler way to build agents without rebuilding the execution layer. It handles orchestration, tools, context, and controls so you can focus on your agent’s skills and outcomes. Watch @jeffhollan's demo to see it in action.

Jack Weis has a Ph.D. in chemical engineering from Ivy League powerhouse Princeton. His research on ice formation was cited by the Nobel committee. Now he can’t even get a food-prep job with a company that sells frozen crab cakes.  Since graduating in 2024, Weis has applied to more than 2,300 jobs and still hasn’t landed one, according to The Wall Street Journal. He started with pharmaceutical science roles and national lab fellowships. When that didn’t work out, he widened his search to software engineering and eventually frozen crab prep. Two years after finishing his doctorate, Jack Weis is living in his parents’ basement. “It’s quite surprising,” said his mom. “I don’t know how to put it together.” His story reflects a frozen job market for college graduates. Economists call it a “low-hire, low-fire” environment, where workers stay put and openings stay scarce. Long-term unemployment this summer hit its highest level in over a decade outside the pandemic, and AI screening tools are making it harder for applicants to reach a human. Read more:

SpaceX literally turns engineering into magic It's like watching a sci-fi version of reality unfold right before your eyes