Opinion editorial
Medium
@simonw
Importance score: 4 • Posted: March 09, 2026 at 13:40
Score
4
A short note that the predictions that LLMs would favor "boring technology" that's over-represented in the training data don't appear to be playing out as expected with the latest models - once you attach them to a good coding agent harness at least https://simonwillison.net/2026/Mar/9/not-so-boring/
Grok reasoning
Challenges common LLM prediction with evidence from coding agents, from influential developer @simonw.
Likes
318
Reposts
22
Views
62,808
Tweet ID: 2031002164165021868
Prompt source: ai-influencers-news
Fetched at: March 10, 2026 at 05:41