Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
@teortaxesTex
Depending on how you measure, Anthropic's models are *faster* than DeepSeek-Flash now. They have curiously long TTFT on API, though.
(I guess this is complete bullshit and they're doing screening/rewriting and then stream tokens with delay? Might also help them hide batching)
(I guess this is complete bullshit and they're doing screening/rewriting and then stream tokens with delay? Might also help them hide batching)
AJ@ItsmeAjayKV · Oct 10Deepseek v4.1-flash is insane.
Going back to other models feels way slower and discouraging.
v4.1-flash is below GLM-5.3-flash for quality, but i'm still sticking with v4.1-flash more because it can build and iterate way faster lol.
Going back to other models feels way slower and discouraging.
v4.1-flash is below GLM-5.3-flash for quality, but i'm still sticking with v4.1-flash more because it can build and iterate way faster lol.
Open quoted post →
16 141