Understand this story
On November 3, 2026, Ethan Mollick publicly commented on attempts to reproduce old LLM research findings at scale using new models, calling it a good idea. He stated that much of the existing understanding about LLMs is already outdated: recent models no longer fabricate citations, and both hallucination rates and stereotyping have declined, but sycophantic tendencies and a left-leaning stance still persist. There have been no subsequent developments so far.
AI-generated from public reports
Latest update · Discussion
Kol Tregaskes joined this discussionDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 3
Kol TregaskesRelated discussion
Kol Tregaskes joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
AI WillRelated discussion
AI Will joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Ethan Mollick
Ethan Mollick on the study replicating old LLM conclusions
Ethan Mollick praised the idea of using new models to replicate old LLM research findings at scale, arguing that much of the existing understanding is outdated: recent models no longer fabricate citations, and both hallucination rates and stereotypes have declined, but sycophantic tendencies and a left-leaning stance still persist.
Heat trend for this story
- Current
- 17
- Period peak
- 26 Nov 3 21:00
- 24-hour change
- —
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.