Gemini 4 Carbon, a low-cost AI model, is significantly slower than comparable models Opus and Astra, with tasks taking up to 1 hour, compared to minutes for Opus and 22 minutes for Astra. Analysis reveals that slower inference, unnecessary work, and mechanical inefficiencies, such as re-reading code and making fewer tool calls, contribute to the slowness. These inefficiencies account for 25% of Carbon's excess runtime. AI summary
Firehose
Filtered to Hacker News, tagged “delay” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives