March 1, 2023@elonmusk →
“@O42nl @kirillgroshkov Tesla does INT8 inference. Way more efficient than FP16, but took us a lot of effort to overcome quantization errors.”
Engagement vs. median curated tweet
1.3K
Likes
85
Retweets
91
Replies
Companies involved
Other tweets from the same period
“Stage 1 to stage 2 mass ratio is too high on Falcon 9, necessitating a long entry burn. This is fixe…”
Mar 3, 202318.9K likes
“Another launch”
Mar 3, 202337.0K likes
““I used to be in crypto, but now I got interested in AI"”
Mar 3, 2023Viral250.4K likes
“@Cernovich @JackPosobiec That is the goal”
Mar 3, 20237.4K likes
