Загрузка видео...

Не удалось загрузить видео

На главную

SpaceXAI just dropped the best 1-hour workshop on token efficiency for Grok Bot: what burns your budget and how to run 20 agents on the same spend 02:15 - What tokens actually are 13:10 - Why context eats 90% of most people's spend 17:08 - Model selection 26:21 -...

36,848 просмотров • 2 дней назад •via X (Twitter)

Комментарии: 6

Фото профиля Ricker
Ricker2 дней назад

top tier watch broski

Фото профиля kadd
kadd2 дней назад

Great share bro. Bookmarked

Фото профиля Kuzka_aaa
Kuzka_aaa2 дней назад

The point about context eating 90% of most people's spend (13:10) really resonates. What's the single biggest lever you've found for cutting context bloat without losing output quality?

Фото профиля AI Mastery Guide
AI Mastery Guide2 дней назад

Context eating 90 percent explains a lot

Фото профиля Zero G Talent
Zero G Talent1 день назад

We saw the exact same thing when scaling the first few hardware test beds. Getting the token overhead down is the only way to keep real time loops from falling behind!

Фото профиля Dalton Connett
Dalton Connett1 день назад

Nice! It helps so much to have individual jobs for different bots

Похожие видео