Sources: ByteDance is pre-training an AI model with up to 10T parameters, roughly 3x Kimi K3 and potentially larger than estimates for Anthropic's Mythos 5 (Financial Times)
ByteDance is reportedly pre-training a 10T-parameter model, signaling a major scale-up in China’s frontier AI race.
Excerpt
<a href="https://www.ft.com/content/9b8383b1-a28d-4940-8c4e-2f0cd21556ef"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260807/i2.jpg" vspace="4" /></a>
<p><a href="https://www.techmeme.com/260807/p2#a260807p2" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="https://www.ft.com/">Financial Times</a>:<br />
<span style="font-size: 1.3em;"><b><a href="https://www.ft.com/content/9b8383b1-a28d-4940-8c4e-2f0cd21556ef">Sources: ByteDance is pre-training an AI model with up to 10T parameters, roughly 3x Kimi K3 and potentially larger than estimates for Anthropic's Mythos 5</a></b></span> — TikTok owner training a model three times larger than Moonshot's Kimi K3 — ByteDance is training an AI model that could approach … </p>
Read at source: https://www.techmeme.com/260807/p2#a260807p2