Vanishing Gradients

Кризис надежности ИИ-агента: что происходит, когда инструменты выходят из строя в процессе произв...

Кризис надежности ИИ-агента: что происходит, когда инструменты выходят из строя в процессе произв...
10x Your Productivity by Building Personal Agents with MCP

10x Your Productivity by Building Personal Agents with MCP
Patterns and Anti-Patterns For Building with AI (with John Berryman)

Patterns and Anti-Patterns For Building with AI (with John Berryman)
AI Agents and LLM Judges at Scale: Processing Millions of Documents (Without Breaking the Bank)

AI Agents and LLM Judges at Scale: Processing Millions of Documents (Without Breaking the Bank)
DeepMind Just Dropped Gemma 270M... And Here’s Why It Matters

DeepMind Just Dropped Gemma 270M... And Here’s Why It Matters
The Map is Not the Territory: Bryan Bischof on RAG Systems, Representations, and Retrieval

The Map is Not the Territory: Bryan Bischof on RAG Systems, Representations, and Retrieval
Why Most LLM Products Break at Retrieval (And How to Fix Them)

Why Most LLM Products Break at Retrieval (And How to Fix Them)
Why We Built an MCP Server and What Broke First -- With Philip Carter, Honeycomb

Why We Built an MCP Server and What Broke First -- With Philip Carter, Honeycomb
A Field Guide to Rapidly Improving AI Products -- With Hamel Husain

A Field Guide to Rapidly Improving AI Products -- With Hamel Husain
How To Benchmark AGI -- With Greg Kamradt, President of ARC-AGI

How To Benchmark AGI -- With Greg Kamradt, President of ARC-AGI
When Vibe Coding Works: Greg Built a Chrome Extension to Query GitHub CSVs with SQL

When Vibe Coding Works: Greg Built a Chrome Extension to Query GitHub CSVs with SQL
Vibe Coding the JFK Docs with Claude, OCR, and Next.js 🕵️‍♂️

Vibe Coding the JFK Docs with Claude, OCR, and Next.js 🕵️‍♂️
How to Evaluate LLM Apps Before You Launch

How to Evaluate LLM Apps Before You Launch
Debugging LLMs? Start with Your Data – Hamel Husain

Debugging LLMs? Start with Your Data – Hamel Husain
Creating Physical Products with Generative AI: A Demo with Dan Becker (Build Great AI)

Creating Physical Products with Generative AI: A Demo with Dan Becker (Build Great AI)
Data Science Tools Reimagined: From arXiv Search to Scikit-learn | Vincent Warmerdam

Data Science Tools Reimagined: From arXiv Search to Scikit-learn | Vincent Warmerdam
Rasa CALM Demo: Conversational AI with LLMs | Alan Nichol

Rasa CALM Demo: Conversational AI with LLMs | Alan Nichol
The skills you need to work with LLMs

The skills you need to work with LLMs
The hardware you need to work with LLMs

The hardware you need to work with LLMs
Prompt Engineering vs RAG vs Fine-Tuning

Prompt Engineering vs RAG vs Fine-Tuning
Reinforcement Learning with Human Feedback 101

Reinforcement Learning with Human Feedback 101
LLM Research Techniques: LoRA, DPO, Mixture of Experts, and more

LLM Research Techniques: LoRA, DPO, Mixture of Experts, and more
The Full LLM Lifecycle

The Full LLM Lifecycle
Fine-Tuning GPT-2 to create a spam classifier in 30 seconds!

Fine-Tuning GPT-2 to create a spam classifier in 30 seconds!
What exactly is end-to-end data science?

What exactly is end-to-end data science?
Data science failure modes

Data science failure modes
Measuring success in data science

Measuring success in data science
The importance of rapid prototyping in data science and R Shiny

The importance of rapid prototyping in data science and R Shiny
The biggest value of data science (hint: it's NOT ML or AI)

The biggest value of data science (hint: it's NOT ML or AI)