OpenAI's Codex now offers three ways to interact with computers—Computer Use for native apps, Chrome for signed-in sites, and an in-app browser for pages—enabling tasks like getting a refund from Amaz…
Shifting from using coding agents solely for software development to applying them broadly for "knowledge work," such as creating presentations and spreadsheets. This behavioral change was driven by f…
Six progressive levels of complexity for using Codex's AI to create a morning brief, starting with a simple prompt that connects Slack, Gmail, and Calendar to summarize the user's day. It then advance…
The author is discontinuing their 567 Labs courses as of February 2, 2026, and releasing all course transcripts as open-source ebooks for public access. The material includes a RAG playbook emphasizin…
Based solely on the provided text, the article explains that the key difference between engineers who successfully leverage AI and those who do not is not talent, but workflow. Engineers who treat AI …
Guide to Retrieval-Augmented Generation (RAG), a technology that combines information retrieval with language generation to enhance AI applications. It covers fundamental concepts, key terms, and a se…
Lexical search remains crucial in RAG systems despite the dominance of semantic search, as it excels at exact matching, handling niche jargon, and efficient filtering. It describes lexical search's in…
The article, based on insights from AI practitioner Skylar Payne, identifies common anti-patterns in Retrieval-Augmented Generation (RAG) systems that degrade performance. Key mistakes include silent …
Cognition avoids multi-agent systems for coding tasks because they suffer from context loss, akin to a "game of telephone," where critical information is miscommunicated between agents. The company fo…
Anton Troynikov from ChromaDB emphasized that examining both the data and user queries is a critical first step for optimizing RAG system performance, as misalignment between stored data and user need…
Fine-tuning re-rankers and embedding models can boost RAG system retrieval performance by up to 12%, with re-rankers acting as a plug-in between initial retrieval and the LLM. It details training appr…
Public benchmarks like MTEB are unreliable for evaluating embedding models in real-world retrieval systems because their generic, artificially clean data does not reflect actual user behavior or domai…
Glean builds custom embedding models for each customer because enterprise data is highly heterogeneous, containing diverse sources like Slack messages, GitHub code, and meeting transcripts, along with…
A speaker series hosted by the author, featuring teams from leading coding agent companies like Cognition, Sourcegraph, Cline, and Augment. A key finding across all discussions is that simpler approac…
Insights from Chris Lovejoy, Head of Clinical AI at Anterior, on building AI agents for specialized industries. He identifies two key challenges: the "last mile problem" of adapting powerful models to…
Discussion with ChromaDB's Anton on text chunking strategies for RAG applications, explaining that chunking remains critical for retrieval efficiency and accuracy regardless of LLM context window size…
According to the article, a team building an agent for the SWE-Bench coding evaluation found that simple tools like `grep` and `find` were more effective than complex embedding-based retrieval, as the…
The article, featuring insights from Ben and Sidhant, explains that AI systems often fail in production because traditional monitoring tools like Sentry are insufficient, as AI errors lack explicit er…