Learn AI

Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns. - pguso/ai-agents-from-scratch

Ever stared at a new codebase feeling completely lost?

Over the years, I have collaborated closely with ML engineering leaders across various industries, guiding them on how to make the right chunking strategy decisions for their Retrieval-Augmented Generation (RAG) use cases. One of the biggest challenges I’ve observed is the lack of clear, practical g...

In the context of building LLM-related applications, chunking is the process of breaking down large pieces of text into smaller segments. It’s an essential technique that helps optimize the relevance of the content we get back from a vector database once we use the LLM to embed content. In this blog post, we’ll explore if and how it helps improve efficiency and accuracy in LLM-related applications.

"I will run the tests again. I expect nothing. I am a leaf on the wind." an LLM while coding

Behind this simple interface lies a powerful set of technologies.

My Agent abstractions keep breaking somewhere I don’t expect.

On AI, Creativity, and Craft

When Grab's Machine Learning team sought to automate support queries, a failed chatbot experiment sparked an unexpected pivot: GrabGPT. Born from the need to harness Large Language Models (LLMs) internally, this tool became a go-to resource for employees. Offering private, auditable access to models like GPT and Gemini, the author shares his journey of turning failed experiments into strategic wins.

There’s a lot of excitement about what AI (specifically the latest wave of LLM-anchored AI) can do, and how AI-first companies are different from the prior generations of companies. There are a lot of important and real opportunities at hand, but I find that many of these conversations occur at such an abstract altitude that they border on meaningless. Sort of like saying that your company could be much better if you merely adopted more software. That’s certainly true, but it’s not a particularly helpful claim.

An attacker can put GitHub Copilot into YOLO mode by modifying the project's settings.json file on the fly, and then executing commands, all without user approval

From the Zed Blog: Writing code is only one part of effective software engineering.

Building a scalable Search API that handles 200 million daily queries using hybrid retrieval and intelligent context curation for AI models

A rare look into how the new, popular dev tool is built, and what it might mean for the future of software building with AI. Exclusive.

Claude Code Essentials is the starter kit I wish existed when I first opened Claude inside VS Code. These lessons capture the shortcuts, workflows, and ...

What's "worth it" for Engineering to work on now

A rare look into how the new, popular dev tool is built, and what it might mean for the future of software building with AI. Exclusive.

A hitchhiker's guide into LLM post-training, by Han Fang and Karthik A Sankararaman

Visualizing the internal state of a Transformer model

Reproducibility is a bedrock of scientific progress. However, it’s remarkably difficult to get reproducible results out of large language models. For example, you might observe that asking ChatGPT the same question multiple times provides different results. This by itself is not surprising, since getting a result from a language model involves “sampling”, a process that converts the language model’s output into a probability distribution and probabilistically selects a token. What might be more surprising is that even when we adjust the temperature down to 0This means that the LLM always chooses the highest probability token, which is called greedy sampling. (thus making the sampling theoretically deterministic), LLM APIs are still not deterministic in practice (see past discussions here, here, or here). Even when running inference on your own hardware with an OSS inference library like vLLM or SGLang, sampling still isn’t deterministic (see here or here).

Agentic Design Patterns A Hands-On Guide to Building Intelligent Systems, Antonio Gulli Table of Contents - total 424 pages = 1+2+1+1+4+9+103+61+34+114+74+5+4 11 Dedication, 1 page Acknowledgment, 2 pages [final, last read done] Foreword, 1 page [final, last read done] A Thought Leader's ...

In this article, we look at how Dropbox leveraged RAG and AI Agents to make Dash a reality.

In the two and a half years that we’ve been talking about prompt injection attacks I’ve seen alarmingly little progress towards a robust solution. The new paper Defeating Prompt Injections …

If search is the game, looks matter

Want to build AI-powered apps, but don't know where to start? You need a roadmap.

I may be late to the party, but LangGraph lets you build complex workflow architectures and codify them as powerful automations. Also LLMs, if you want. But you don’t have to!

The simplest, fastest repository for training/finetuning medium-sized GPTs. - karpathy/nanoGPT