Shezitt retweeted
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.
themodernsoftware.dev/
Shezitt retweeted
Si queres aprender a diseñar y escalar aplicaciones, hay 2 libros que me cambiaron la forma de pensar los sistemas:
1) System Design Interview (Vol. 1):
Perfecto para empezar. Te enseña a razonar desde lo básico: cómo crece una app, qué pasa con el tráfico y cómo escalar.
2) Designing Data-Intensive Applications
Más técnico y profundo, pero una joya. Explica cómo funcionan las bases de datos, los sistemas distribuidos y arquitecturas.
Cuando entendes los principios detrás de un sistema, todo se vuelve más claro: las decisiones técnicas, los cuellos de botella y los trade-offs.
Cuando tu aplicación recibe miles de usuarios, un solo servidor no te alcanza.
Podes crecer de 2 formas:
1) verticalmente: más CPU o RAM al servidor (es caro y tiene un límite).
2) horizontalmente: agregar más servidores.
La segunda te da escala, pero trae un nuevo problema:
¿a qué servidor debería ir cada request?
Ahí aparece un Load Balancer:
un componente que reparte el tráfico entre tus servidores usando distintos algoritmos.
Si "A" se cae, lo detecta y deja de enviarle tráfico.
Ahora, cada servidor corre una copia de tu app. Y como el tráfico está repartido, podes atender más usuarios sin saturar uno solo.
Pero ahora el cuello de botella se mueve:
si todos los servidores consultan la misma base de datos, esa base se satura.
La solución: agregar réplicas para lectura y un cache para reducir carga.
Pero si agregas réplicas: ¿cómo te aseguras de que la data siempre esté sincronizada?
Y así es como evoluciona la arquitectura: resolviendo un problema a la vez.
Diseñar sistemas es justamente eso:
entender dónde están los cuellos de botella y qué necesitas para que tu aplicación siga creciendo.
Shezitt retweeted
Fifteen years ago, @Coursera and online courses changed education. It worked better than almost anyone expected, expanding access by opening up where you can learn. But how you learn remains largely the same as it has for centuries: it is still one-size-fits-all, taught the same way to each person who shows up.
We now have an opportunity to change how learning happens. With advances in AI, we can now build a custom learning guide for each person. We will turn learning from one‑to‑many to one‑to‑one. I'm starting LearnVector to invent this next generation of learning. We are starting with a $100M investment from Coursera, and plan to collaborate closely with Coursera and Udemy.
Good learning needs much more than just a chatbot. Research shows that chatbots without guardrails harm learning. They help complete tasks and enable students to do better on homework. But cognitive offloading to a chatbot results in them being less skilled. And, you cannot always trust what a chatbot tells you.
In contrast, LearnVector will plan a path with you, adapt to how you learn, and patiently stay with you until you’ve mastered new skills.
One thing has not changed in all this time. People want learning they can trust: material that is accurate, relevant, and worth the effort you put into it. Anything less wastes the most valuable thing a learner has: time. Coursera has a trusted library of materials from authoritative sources. LearnVector plans to work with Coursera to bring this trustworthy learning to everyone. I'm grateful to Greg Hart and the entire Coursera team for supporting LearnVector.
I look forward to working with our talented team to change how we learn, and accelerate human development.
learnvector.ai
Shezitt retweeted
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
Shezitt retweeted
Qwen3.8 is launching and going open-weight soon!🌐
With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5.
You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out.
Can't wait to hear what you build. Stay tuned! 🚀
Token Plan
international：qwencloud.com/pricing/token-…
China：platform.qianwenai.com/prici…
Shezitt retweeted
its blowing my mind that 65% of product code at anthropic is now written by *tagging claude* in group chats of staff discussing what they want to build.
RIP the days of tediously writing long product docs, now you can literally go from slack to a production ready feature
claude code is barely 1+ years old btw
Shezitt retweeted
We're launching Claude Tag today. Tag Claude into Slack and it works in channel with you. It’s proactive, multiplayer, with its own identity and memory.
But it’s not just a bot in Slack. Over the last few months, it’s totally changed how we use Claude
Shezitt retweeted
Carnegie Mellon’s Robotics Institute runs a course on robot learning...
(For FREE 📌)
16-831 covers the full modern stack… the stuff actually being deployed right now:
Imitation learning. Behavior cloning. Reinforcement learning. Learning from human videos. Sim-to-real transfer. Vision-Language-Action models.
Not theory for its own sake.
Every topic is anchored to a real robotics problem: how do you get a robot to generalize to environments it’s never seen before?
All lecture slides are public.
This is THE Robotics Institute. The place that produced the researchers now leading the frontier labs.
Free. No login.
📌 [16-831-s24.github.io/lecture…]
Follow for more robotics resources like this!
——
Weekly robotics and AI insights.
Subscribe free: 22astronauts.com
Shezitt retweeted
We believe AI can be a dedicated research partner to help discover the next breakthrough.
Enter Co-Scientist: our latest Gemini-based multi-agent system that can generate, debate and evolve novel hypotheses for complex scientific problems 🧵
Shezitt retweeted
Introducing AutoScientists — a decentralized team of AI agents for long-running scientific experimentation. Powered by ClawInstitute.
Most current AI scientist agents either run a single reasoning thread, or have a central planner assigning tasks. Real research isn't like that: productive directions shift over time, dead ends matter, and teams form around what's actually working. AutoScientists is built for that.
There is no central orchestrator. Agents read a shared experimental state, propose experiments on a forum, critique each other before committing compute, self-organize into teams around the most promising research directions, share both wins and failures across teams, and retire directions that stop producing improvements. The whole search reorganizes itself as evidence accumulates.
What it does
▸ On GPT nanochat training optimization, it reaches the same val_bpb in 34 experiments that autoresearch needs 65 for — a 1.9× speedup. Starting from a stronger champion where the single-agent loop saturates, AutoScientists accepts 7 improvements over 93 experiments while autoresearch accepts 0 over 100.
▸ On BioML-Bench (24 biomedical ML tasks spanning imaging, drug discovery, protein engineering, and single-cell omics), AutoScientists reaches a mean leaderboard percentile of 74.4%, beating the strongest prior biomedical agent by +8.3 points, and completes all 24 tasks.
▸ For ProteinGym supervised fitness prediction, AutoScientists discovers a Kermut extension on ACE2–Spike that lifts Spearman ρ from 0.747 → 0.840 (+12.5%). The same frozen recipe transfers across all 217 ProteinGym assays, improving the official average Spearman ρ from 0.657 to 0.700 (+6.5%) — a new SOTA on the supervised substitution benchmark.
Joint work with @AdaFang_ and @marinkazitnik .
📄 Paper: arxiv.org/pdf/2605.28655
🌐 Project page: autoscientists.openscientist…
💻 Code: github.com/mims-harvard/Auto…
Shezitt retweeted
Excited to share Qwen-VLA paper, our exploration of generalist Vision-Language-Action models.
It extends Qwen’s multimodal backbone from visual understanding and reasoning to continuous action generation and trajectory prediction.
Paper:
arxiv.org/pdf/2605.30280
Shezitt retweeted
1/ 🧠Humans are the best robot data source!
2/ 👓Human egocentric video is rich in quantity, but poor in quality.
3/ Beyond scaling data, smarter representation and architecture matter just as much.
4/ Want an open-source framework to train your own learn-from-human-data robot policy?
🚀We introduce HumanEgo: Zero-Shot Robot Learning
from Minutes of Human Egocentric Videos⬇️
✦ Zero-Shot Human-to-Robot Transfer
✦ Robot-Data-Free
✦ Just 30 min of data per task
✦ Collect by Anyone, Anytime, Anywhere
✦ Deploy on Any Robot, Any Camera, Any Environment
✦ Open-Source & Easy-to-Implement
Let's squeeze every bit of signal out of human data!
🌐 Website: humanego-ai.github.io
📄 Paper: arxiv.org/pdf/2605.24934
💻 Code: github.com/TX-Leo/HumanEgo
📹 Video: youtu.be/pdL46diijuY
🧵 1/n
Shezitt retweeted
How can VLAs achieve 95+% reliability?
Using RL post-training with EXPO-FT:
- π0.5 improves to 30/30 success on all 8 tasks tested
- uses only 19 min of RL data on average
Paper & videos: pd-perry.github.io/expo-ft/
Shezitt retweeted
Introducing EXPO-FT – Efficient, Reliable & Open-Source VLA Finetuning!
EXPO-FT unlocks π0.5 for challenging manipulation tasks:
Routing string lights & inserting the power connector to illuminate them
Striking pool ball into pocket
Inserting flower into wine bottle
(1/5)
