Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

> "Agents produce overly verbose code that's hard to read and understand" Try setting a Cognitive Complexity rule in Biome. This metric is specifically designed to test how hard the code is to understand

asidorenko_'s profile picture

Alex Sidorenko

35,405 subscribers

110,420 Aufrufe • vor 16 Tagen •via X (Twitter)

Nachrichten & PolitikBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

13 Kommentare

Profilbild von Alex Sidorenko
Alex Sidorenkovor 16 Tagen

Paper on cognitive complexity

Profilbild von Gabriel Moncha
Gabriel Monchavor 15 Tagen

isn't this cyclomatic complexity?

Profilbild von Alex Sidorenko
Alex Sidorenkovor 15 Tagen

Nope

Profilbild von Gabriel Moncha
Gabriel Monchavor 15 Tagen

it looks like it is but it's count differently

Profilbild von khushal
khushalvor 16 Tagen

interesting might go well with my /ponytail & knip workflow

Profilbild von Fayi
Fayivor 15 Tagen

a diff of what actually changed would have been nice

Profilbild von l’étranger
l’étrangervor 15 Tagen

Cool. Does it do well?

Profilbild von Buswe
Buswevor 16 Tagen

Worth knowing maxAllowedComplexity defaults to 15, so pinning it lower in the agent's lint step makes the feedback land right away.

Profilbild von Scept Meerkat
Scept Meerkatvor 15 Tagen

Metrics, when they are optimised for, always have side-effects that make code worse.

Profilbild von 0xbagg
0xbaggvor 15 Tagen

why isn’t it on automatically?

Profilbild von Anton Haskevych
Anton Haskevychvor 15 Tagen

Biome is awesome Ai agents (and people too) will write good code if you enforce it I would love to see biome have some rules that wnforce stricter quality for AI agents Personally, I already create rules for layers and naming conventions - a lot of ideas from archunit

Profilbild von Pronsh
Pronshvor 16 Tagen

I like

Profilbild von rex 🇪🇸🇷🇴
rex 🇪🇸🇷🇴vor 15 Tagen

"fix lint" and it just turns the lint off

Ähnliche Videos

Stage is a code review platform designed to help engineers understand AI-generated code. Your team is drowning in an endless backlog of PRs. Stage turns code review into a guided process and enables you to review changes faster than using GitHub. Congrats on the launch, Charles Pan and Dean Stratakos!
0:50

Stage is a code review platform designed to help engineers understand AI-generated code. Your team is drowning in an endless backlog of PRs. Stage turns code review into a guided process and enables you to review changes faster than using GitHub. Congrats on the launch, Charles Pan and Dean Stratakos!

Y Combinator

1,063,689 Aufrufe • vor 4 Monaten

I wonder why this is so hard to understand
1:57

I wonder why this is so hard to understand

ELAYAS° FC

67,160 Aufrufe • vor 2 Monaten

Why is this so hard for Catholics to understand?
0:48

Why is this so hard for Catholics to understand?

Catholics for Catholics 🇺🇲

248,127 Aufrufe • vor 1 Jahr

Aidan rejecting Priya for the 20th time in this episod,how hard is it for u to understand priyaaaa #Loveisland #LoveislandUK
2:02

Aidan rejecting Priya for the 20th time in this episod,how hard is it for u to understand priyaaaa #Loveisland #LoveislandUK

TrendShift 🍵 ⏳

30,339 Aufrufe • vor 1 Monat

arXiv -> quickarXiv Papers are often written in convoluted language that is hard to understand Swap arXiv -> quickarXiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with Z.ai's GLM OCR 🚀 Also includes code + author tweet
0:27

arXiv -> quickarXiv Papers are often written in convoluted language that is hard to understand Swap arXiv -> quickarXiv on any paper URL to get an instant blog with figures, insights, and explanations. Now extracted with Z.ai's GLM OCR 🚀 Also includes code + author tweet

alphaXiv

74,591 Aufrufe • vor 26 Tagen

Y all don't understand how hard this song is I've been listenin to it all day
2:06

Y all don't understand how hard this song is I've been listenin to it all day

K2 yb enthusiast

24,142 Aufrufe • vor 1 Monat

When adding padding and size boxes becomes a bit verbose, it's time to add a Gap. 🤔 In this #PackageoftheWeek throwback, we'll show you how to add some space around your widgets without making your code harder to read →
0:20

When adding padding and size boxes becomes a bit verbose, it's time to add a Gap. 🤔 In this #PackageoftheWeek throwback, we'll show you how to add some space around your widgets without making your code harder to read →

Flutter

30,119 Aufrufe • vor 2 Jahren

we need ways to stay oriented and understand - what's in a codebase - what are my agents working on - what are they looking at - what they've changed &c something in between "read a summary in chat" and "read every line of code"
2:23

we need ways to stay oriented and understand - what's in a codebase - what are my agents working on - what are they looking at - what they've changed &c something in between "read a summary in chat" and "read every line of code"

Amelia Wattenberger 🪷

10,525 Aufrufe • vor 5 Monaten

Elon Musk: ”The tax code is, you could fill this room with tax credits. Only an AI could even understand the tax code. Maybe. We want to have a tax code you can actually read as a human. I’m very much in favor of small government. We want minimal government action and maximum freedom for the people, and that is what leads to the highest level of prosperity.”
0:37

Elon Musk: ”The tax code is, you could fill this room with tax credits. Only an AI could even understand the tax code. Maybe. We want to have a tax code you can actually read as a human. I’m very much in favor of small government. We want minimal government action and maximum freedom for the people, and that is what leads to the highest level of prosperity.”

Taya Bass

17,625 Aufrufe • vor 2 Monaten

Claude Code is CRACKED at design now and I don't think people understand how BIG this is. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)
0:37

Claude Code is CRACKED at design now and I don't think people understand how BIG this is. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

Prajwal Tomar

106,397 Aufrufe • vor 2 Monaten

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools
1:05:42

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools

Jared Zoneraich

13,936 Aufrufe • vor 8 Monaten

Trying to understand a codebase? This technique BLEW MY MIND. Reto Meier told me to try uploading a code repo (after flipping all files to txt) and asking Google AI NotebookLM ( to make a podcast from just the code. It did, and it was crazmazing.
8:00

Trying to understand a codebase? This technique BLEW MY MIND. Reto Meier told me to try uploading a code repo (after flipping all files to txt) and asking Google AI NotebookLM ( to make a podcast from just the code. It did, and it was crazmazing.

Richard Seroter

20,869 Aufrufe • vor 2 Jahren

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!
2:17

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 Aufrufe • vor 1 Jahr

If you're still using VS Code, you're falling behind. is like if VS Code and ChatGPT had a baby, and it's beautiful. Just watch the video — you have to see it to understand.
0:38

If you're still using VS Code, you're falling behind. is like if VS Code and ChatGPT had a baby, and it's beautiful. Just watch the video — you have to see it to understand.

Matt Shumer

301,094 Aufrufe • vor 3 Jahren