A technical guide providing a bash script workaround to fix Ollama model download failures and connection resets.
A summary of Chip Huyen's chapter on AI fine-tuning, arguing it's a last resort after prompt engineering and RAG, detailing its technical and organizational complexities.
Using DeepSeek AI to write and refine a Java solver for the 'Crazy Cheeze' puzzle, exploring code generation and evaluation.
A software engineer explores using LLMs and R code to analyze GitHub activity to track and summarize their weekly work, addressing the challenge of remembering tasks.
Argues that generative AI creates wasteful communication and advocates for concise, human-driven interactions instead.
Argues that minimal standard libraries in languages like Rust and JavaScript lead to an explosion of transitive dependencies, harming maintainability.
A technical guide to the lifecycle management and update process for Azure Local 23H2, focusing on the new Lifecycle Manager.
A guide on using Terraform for multi-cloud infrastructure deployment across Google Cloud and AWS, covering IaC benefits and best practices.
Critique of modern dependency bloat in software development, advocating for simpler, minimal-dependency designs.
PostgreSQL 18 will allow dynamic adjustment of autovacuum_max_workers without a server restart, improving database maintenance flexibility.
A tutorial on building multi-agent AI systems using Python and Azure OpenAI, covering concepts, frameworks, and practical implementation.
Analysis of Chapter 6 from Chip Huyen's 'AI Engineering' book, focusing on RAG systems and AI agents, their architecture, costs, and relationship.
Schedule of public tech talks and workshops on frontend development, JavaScript, and web standards for the first half of 2025.
An indie developer analyzes the key factors behind the organic success of their app, Burnout Buddy, focusing on App Store Optimization and solving a personal problem.
A curated list of 12 influential LLM research papers from 2024, highlighting key advancements in AI and machine learning.
A curated list of 12 influential LLM research papers from each month of 2024, covering topics like Mixture of Experts, LoRA, and scaling laws.
A guide to using typos-cli, a Rust-based command-line spell checker for detecting and fixing typos in code and documentation.
A call to discuss transparency and governance issues at FOSDEM '25 following the cancellation of a controversial sponsored keynote talk.
A technical guide on aligning open-source large language models (LLMs) in 2025 using Direct Preference Optimization (DPO) and synthetic data.
