teapawt
$
MidbrainAI
@MidbrainAI
Building the persistent experience layer for proactive intelligence
Joined October 2024
Tweets
2
Following
3
Followers
33
Likes
10
Tweets
Tweets & Replies
Reposts
Media
Search
Timeline
Grid
Gallery
MidbrainAI
@MidbrainAI
Nov 5
83.2% on DolphinBench, across 600 tests. Same agent and model as the leaderboard: Hermes with GPT 5.6 Luna. $64 in harness cost, plus 52k memory credits. Production MidBrain, with two experimental prefetch features on.
1
1
3
118
Load more