Reading up on GPT-5 mini
3 deep · digging since nov 25, 25
- How LLMs Distort Our Written Language
LLMs distort written language by shifting semantics, altering conclusions, and removing personal voice, even when instructed to make minimal edits.
- Can agents replace the search stack?
Using a basic BM25 or e5 retriever with an LLM agent can achieve 0.289→0.453 NDCG on Amazon ESCI by reasoning over queries, but this approach fails on passage retrieval where the embedding model already knows best.
- Introducing shopping research in ChatGPT
OpenAI launches shopping research in ChatGPT, a conversational tool that researches products and builds personalized buyer's guides using GPT-5 mini.