Warning: Next-generation AI models show signs of "going in circles"
Bindu Reddy points out that the latest updates to Opus, Gemini, and Sonnet are showing poorer performance or more bugs compared to their predecessors.
Sources x.com
Bindu Reddy points out that the latest updates to Opus, Gemini, and Sonnet are showing poorer performance or more bugs compared to their predecessors.
The PapersWithCode project officially returns with the support of AI agents, helping to automatically aggregate SOTA leaderboards, research methods, and code from the latest papers.