We (I) need science
Argues for rigorous scientific studies on the impact and risks of using LLMs in software development, highlighting current lack of impartial research.
Argues for rigorous scientific studies on the impact and risks of using LLMs in software development, highlighting current lack of impartial research.
A technical architect explores using local LLMs as junior developers for a blog migration, analyzing their strengths and common pitfalls.
Tutorial on using Dremio's AI_GENERATE SQL function to extract structured data from unstructured text like emails and contracts.
A tutorial on using Dremio's AI_CLASSIFY SQL function to categorize data like customer sentiment and support tickets directly within a data lakehouse.
Tutorial on using Dremio's AI_COMPLETE SQL function to generate product summaries, marketing copy, and translations directly within a data pipeline.
Explores the 'Great Transition' where AI, especially LLMs and skills, is making specialized knowledge public, reshaping knowledge work and expertise.
Discusses the discovery of LLM-generated commits in the CPython repository and the implications for open-source development.
A skeptic's detailed journey using AI coding agents to port scikit-learn to Rust, showcasing the surprising capabilities of modern LLMs.
A skeptic's detailed journey using AI coding agents for complex projects, including porting scikit-learn to Rust, showcasing their surprising capabilities.
A monthly roundup of tech links focusing on data engineering, Kafka, AI, and software development, including personal articles and industry news.
Explains why AI data analytics fail without a semantic layer to define business metrics and ensure accurate, secure queries.
Anthropic's Claude Code creator discusses the evolving role of engineers and why developers are still crucial in the AI era.
A daily tech reading list covering AI advancements, API latency fixes, cloud scaling, and the importance of fundamentals over frameworks.
Martin Fowler shares insights from a software retreat on how LLMs impact senior, mid-level, and junior developers, and discusses cognitive debt.
A daily tech reading list covering AI agents, platform engineering, API docs, AI UX, and cloud performance trends.
The New York Times uses a custom AI tool called the 'Manosphere Report' to track and analyze podcast content for news coverage.
Introduces GLM-5, a massive new open-source AI model, and discusses the emerging concept of 'Agentic Engineering' for software development with LLMs.
GLM-5, a massive new 754B parameter open-source AI model, is discussed in the context of the emerging field of 'Agentic Engineering' for software development.
A research paper analyzes LLM performance on SQL generation tasks using different structured data formats and large schemas, comparing frontier and open-source models.
Research paper analyzes LLM performance on large SQL schemas, comparing 11 models across 4 data formats for structured context engineering in agentic systems.