Mia (@MiaAI_lab)
@MiaAI_lab
0 正在关注 0 粉丝
Time to reveal!
Ox Alpha is Zai's GLM Flash 🔥
And it's coming out... tonight!
I’m happy to report that Grok 4.6 is just as good as Kimi K3 for everything related to the kernel and modding.
I was testing it almost 8 hours straight non stop, and it's done everything on 'low' effort. It's also much faster and uses significantly fewer tokens.
I'll continue testing it in other areas now.
Great job @SpaceXAI 👏
显示更多
Still haven’t found a real use case where Grok 4.5 fails at something I ask vs GPT-5.6 Sol, Fable 5, or Kimi K3.
All of them are excellent — but Grok 4.5 wins on price and speed by far.
I've inspected the open-sourced Grok Build so you don't have to. Here's exactly what data it sends (and what stays local):
Core (unavoidable)→ Your prompts/conversations + tool calls go to xAI's inference API. That's the whole point of the CLI.
Everything else is off by default — no Mixpanel, no Sentry, no product telemetry unless you explicitly turn it on. Even the auto-update check is a simple version GET you can disable in config.
Purely local stuff (crash reports, debug logs, secret redaction, auth) never touches the network. All telemetry paths also scrub secrets before anything is sent.
Full details 👇
显示更多
Here's one way to get the most from Grok 4.5 ✨
Switching effort to "low" gives strong results on most tasks, near-zero quality loss, big usage savings — plus it's the fastest.
显示更多
