Links from my inbox 2025-12-27 | Dmytro Zharii
image-20251227001921810
Anti-patterns while working with LLMs
instavm.ioAnti-patterns observed while working extensively with LLMs — from redundant context to over‑engineering.
Unsupervised Learning NO. 509
Google Approach to Stopping Prompt Injection, Response to Cory Doctorow's Latest Book/Talk, AI Persuasion Risk, Screens Most Interesting Thing to Kids, and more...