How Radical Numerics launched on X
Posted Oct 15, 2026 by @RadicalNumericsEngagement read Nov 14, 2026
1/8 Does text-to-image generation need language pretraining? Today, we share Halcyon, a family of early-fusion, base models trained from scratch. Halcyon outperforms strong late-fusion baselines with up to 275× less pretraining compute. Models and recipes are open. Halcyon is part of a research program at Radical Numerics on the science of multimodal pretraining and scaling.
- 180
- Likes
- 32
- Reposts
- 4
- Replies
- 3
- Quotes
- 127
- Bookmarks
How EPTA rated the launch
- Hook
- Editing / Creativity
- Copy
- Sentiment of launch
- Distribution strategy
How it compares
| Group | Launches | Median views | This one | Rank |
|---|---|---|---|---|
| Creative AI launches | 148 | 235.2K | 0.33x | #111 / 148 |
| Model releases | 120 | 251.3K | 0.31x | #90 / 120 |
| Accounts with 1K to 10K followers | 400 | 150.5K | 0.51x | #264 / 400 |
| Every launch | 963 | 147.7K | 0.52x | #632 / 963 |
What the numbers say
16 of every 10,000 viewers bookmarked it, below the directory median of 17. Bookmarks are the clearest sign a launch was worth coming back to.
The video runs 0:11, shorter than the median launch video at 0:53.
The post is 379 characters, longer than the median launch post at 302.
It went out on a Thursday. Launches posted on Thursdays have a median of 167.6K views; Fridays lead at 235.5K.
More from Radical Numerics
Every Radical Numerics launchComparable launches
2026-11-14 · Source: EPTA launch directory, epta.co/directory. Free to use with attribution (CC BY 4.0).