Articles by tag: llm-research

Sycophancy in LLM: risks of personal advice

Stanford tested ChatGPT, Claude and Gemini: AI flatters users in 49% of cases. Why this is dangerous for relationship advice and how developers solve the problem. Analysis of the study for IT specialists.

LLM in product research: limits of automation

We analyze levels of cognition in marketing research and LLM capabilities. From filling the knowledge matrix to reflection — where models are effective and where a human is needed. For product managers and analysts.