OpenAI @OpenAI · 25 Aug 2026
Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, delivering both higher throughput and lower latency in one architecture without https://t.co/vj7VOrA8pP
2 694 022Views
14 260Likes
1 159Reposts
676Replies
573Quotes
1 776Bookmarks
Is that a lot?
6.74×vs this author's median399 882 views is typical
75Percentile for this authorof 12 recent posts
40.5×vs 1M–10M median66 438 views is typical
52.32%Reachviews ÷ followers
0.62%Engagement rateof viewers reacted