In this blog post, I dive into an intriguing collection of articles and discussions. From unraveling the complexities of AI data analysts and exploring the misuse of AI to questioning if we’re in a financial bubble, I’ve gathered insights worth sharing. You’ll also find thoughts on the state of the software job market and powerful stories like the impact of technology on our youth. Join me on this enlightening journey!
- Lessons on building an AI data analyst: Text-to-SQL is not enough. Real user questions require multi-step plans, Python, and external context. A semantic layer encodes business meaning and sharply reduces SQL complexity.
- You Have to Feel It:
- Detecting and countering misuse of AI: August 2025: Anthropic’s threat intelligence report on AI cybercrime and other abuses
- Don’t Build Multi-Agents: Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.
- State of the software engineering job market in 2025: ment, the growing importance of location, and more
GERGELY OROSZ
- compiling dinner: . GitHub Gist: instantly share code, notes, and snippets.
- Are We in a Bubble?: In a world of intangible assets, the only way to identify a bubble is to see it pop.
- From “how might we” to “at what cost”: “Don’t move fast and break things when it comes to our kids.” These were the words from the mom of 14 year-old Sewell who ended his life after an ongoing chatbot conversation on Character AI. The…
- FreeDroidWarn: Contribute to woheller69/FreeDroidWarn development by creating an account on GitHub.
- Bear is now source-available:
- The bust files: How NFL teams break young quarterbacks: