In my latest blog post, I’m diving into the world of AI and coding, questioning whether large language models truly understand how to navigate codebases. I’ve shared some interesting reads, like how to harness the power of an unfocused mind, tactics for time management, and the evolving identity of software engineers with AI. Plus, explore the latest on LLM-based workflows, AI’s security challenges, and much more!
- openai/codex: Lightweight coding agent that runs in your terminal –
- Why LLMs Get Lost in Large Codebases: Is it just me, or are the code generation LLMs we’re all using not that good? For months, I’ve watched developers praise LLMs while silently cleaning up their messes, afraid to admit how much babysitting they actually need. I realized that LLMs don’t actually understand codebases — they’re just sophisticated autocomplete tools (with good marketing.) After two years of frustration watching my AI assistants constantly “forget” where files were located, create duplicates, and use completely incorrect patterns, I finally built what the big AI companies couldn’t — or wouldn’t. I decided to find out: What if I could make AI actually understand how my codebase works?
- 3 Ways to Harness the Power of Your Unfocused Mind: Modern productivity culture is obsessed with focus. Here’s why this is sub-optimal.
- How to get control of your time: Two time-use researchers explain how to be mindful about where you spend your precious minutes.
- Stamina is a Quiet Advantage:
- Allocate Time in Each Day for Both Strategic and Tactical Work: In his attempt to emphasize the difference between efficiency and effectiveness, management guru Peter Drucker famously drew a line between “doing things right” and “doing the right things.”
- The Software Engineering Identity Crisis: Many of us became software engineers because we found our identity in building things. Not managing things. Not overseeing things. Building things. With our own hands, our own minds, our own code. But that identity is being challenged. AI coding assistants aren’t just changing how we write software – they’re fundamentally transforming who we are. We’re shifting from creators to orchestrators, from builders to overseers. From engineers to something that looks suspiciously like… managers.
- When No Other Muffin Will Do: you make your own muffins
- An LLM-Based Workflow for Automated Tabular Data Validation: Clean data, clear insights: detect and correct data quality issues without manual intervention.
- Improving Recommendation Systems & Search in the Age of LLMs: Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
- Researchers claim breakthrough in fight against AI’s frustrating security hole: Prompt injections are the Achilles’ heel of AI assistants. Google offers a potential fix.
- Why AI Demands a New Breed of Leaders: Today’s organizations need tech leaders who can also take on the cultural and change management challenges of AI.
- Reproducing Hacker News writing style fingerprinting:
- Unsure Calculator: The Unsure Calculator is an online tool that lets you calculate with numbers you’re not sure about.
- Model Context Protocol Overview – Why You Care!: A look at MCP. What it is, why you need it, how to leverage!🔎 Looking for content on a particular topic? Search the channel. If I have something it will be …
- Train Your Own LLM – Tutorial: This course is designed to help beginners learn how to train a language model from start to finish. Imad will guide you through the whole process, using Moro…
- Behind the 6-digit code: Building HOTP and TOTP from scratch: A while ago, I have started working on authorization and authentication at work. This taught me a lot about how modern authentication systems work. However I have always thought One-Time Password logins are the most mystical ones. A six-digit code that changes every time and can be used to verify
- How Apple and Nike have branded your brain: Powerful branding can not only change how you feel about a company, it can actually change how your brain is wired.