Загрузка видео...

Не удалось загрузить видео

На главную

AI didn't make code cheap. it made bad code lethal. Matt Pocock: "Software fundamentals matter more than ever" AI in a good codebase ships gold. AI in a bad codebase ships garbage. framework mastery doesn't compound. fundamentals do. if you're starting with AI agents, build these 5 patterns before...

28,480 просмотров • 5 месяцев назад •via X (Twitter)

Комментарии: 20

Фото профиля Rohit
Rohit5 месяцев назад

500 AI Agents project here:

Фото профиля Rohit
Rohit5 месяцев назад

Full talk by @mattpocockuk on @aiDotEngineer here:

Фото профиля Nihit Singh
Nihit Singh5 месяцев назад

Crzy

Фото профиля Siddharth
Siddharth5 месяцев назад

fundamentals are gonna stay

Фото профиля Mohamed Anis
Mohamed Anis5 месяцев назад

You've captured exactly why we're seeing such divergent AI outcomes. the quality of underlying architecture determines whether AI accelerates value or amplifies technical debt at scale.

Фото профиля Khairallah AL-Awady
Khairallah AL-Awady5 месяцев назад

banger my man

Фото профиля Alpha Batcher
Alpha Batcher5 месяцев назад

Without these 5 patterns, no work in AI will be successful

Фото профиля J A Z I I
J A Z I I5 месяцев назад

Love it man you cooking with all bangers

Фото профиля CyrilXBT
CyrilXBT5 месяцев назад

banger right here

Фото профиля Crio Songo
Crio Songo5 месяцев назад

You’re 100% right about this. I’ve seen too many teams cut corners on fundamentals just because AI can crank out code fast. I actually just started practicing these 5 agent patterns last week, this post is exactly the reminder I needed.

Фото профиля 唐清乐
唐清乐5 месяцев назад

这句话很准。AI放大的是系统本身的质量,好的工程基础会被加速,坏的抽象也会被更快复制。基础功反而更值钱了。

Фото профиля Morton Digital
Morton Digital5 месяцев назад

That 5th pattern — Building Trustworthy AI Agents — is where most builders get burned in production. Error cascades, retry storms, context loss when the LLM 429s. Put together a playbook on exactly those failure modes:

Фото профиля robertus
robertus5 месяцев назад

bad code used to tax maintainers slowly. agents let it scale its revenge with much better throughput

Фото профиля Himanshu
Himanshu5 месяцев назад

Interesting

Фото профиля Harry Tandy
Harry Tandy5 месяцев назад

a solid architecture is the only thing standing between a working product and a total mess

Фото профиля Levi
Levi5 месяцев назад

the “orchestrator-subagent is the only shape that ships” take is spicy… what breaks first when you skip it

Фото профиля Dylan Swanepoel
Dylan Swanepoel5 месяцев назад

AI amplified one thing more than anything else: Architecture debt. Bad foundations used to slow teams down. Now they poison the output of the agents operating on top of them. That’s why so many AI products demo well but collapse operationally.

Фото профиля robertus
robertus5 месяцев назад

bad code used to tax maintainers slowly. agents let it scale its revenge with much better throughput

Фото профиля Carlos Tecnico
Carlos Tecnico5 месяцев назад

drop F vibe coding. fundamentals or your agent ships trash 🙄

Фото профиля Avid
Avid5 месяцев назад

good one

Похожие видео

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:

Andrew Ng

891,810 просмотров • 1 год назад