I like grok 4.6 more than any anthropic or claude model. I use it in cursor for work, and grok cli for normal os operations/installations/troubleshooting. I also use grok on my phone for normal questions in the supermarket etc.
The problem is Grok is fucking dogshit for 4.6 at generating anything related to dark fiction/angst. It now automatically thinks if u ask for logs, details, etc, it AUTOMATIALLY MEANS ACTIONABLE INSTRUCTIONS.
I've been doing the same thing with Grok 4.6 and the results have been impressive. It plans and gives build instructions to Grok who crushes the code (Fable even said it was better than expected)
it also give 6 or 4 fingers to people, but when you tell him "PEOPLE MUST HAVE FIVE FINDGERS ONLY, DO NOT CHANGE ANYTHING ELSE" its generates different scene
社区评论
精选近 7 天的不同意见，摘录条数不代表真实好评比例。
3 条精选摘录
展开原文
the Cursor model and Grok 4.6 - they get shit done. Maybe not a pretty Greenfield interface, but for the grunt work they are solid and fast.
展开原文
Grok 4.6 = Luna? I don't share that perspective, Grok with Cursor Debug Mode is one of the best models for the price.
展开原文
Grok 4.6 is not, its only made to vibe-code and adjust spreadsheets
展开原文
4.5 that banned everything i tried to do
展开原文
Cursor is worth it because Grok 4.6 is around Opus 4.6 but you get much more usage with it than with Claude Code.
展开原文
I like grok 4.6 more than any anthropic or claude model. I use it in cursor for work, and grok cli for normal os operations/installations/troubleshooting. I also use grok on my phone for normal questions in the supermarket etc.
展开原文
The problem is Grok is fucking dogshit for 4.6 at generating anything related to dark fiction/angst. It now automatically thinks if u ask for logs, details, etc, it AUTOMATIALLY MEANS ACTIONABLE INSTRUCTIONS.
展开原文
I experienced this as well... I tried Grok 4.6 and it doesn't seem to do this.
展开原文
grok 4.6 is not trained for creative writing at all, that's why everyone here is highlighting the downgrade in chat quality
展开原文
I've been doing the same thing with Grok 4.6 and the results have been impressive. It plans and gives build instructions to Grok who crushes the code (Fable even said it was better than expected)
展开原文
Yeah I actually prefer Grok 4.6 but the quotas are so low that I find myself using Codex 5.6 sol medium on their $100 plan.
展开原文
Grok-4.6 is much better. Almost the same level as 4.3. The problem is that after 10-15 replies the answer become completely gibberish
展开原文
Have you tried Grok 4.6, if you're focused on token budgets? In a league of it's own for tokens/intelligence.
展开原文
Coding? No way.
展开原文
agentic coding is top notch since 4.6..ive made a couple of decent mobile games
展开原文
on peut à nouveau faire des roleplays
展开原文
it also give 6 or 4 fingers to people, but when you tell him "PEOPLE MUST HAVE FIVE FINDGERS ONLY, DO NOT CHANGE ANYTHING ELSE" its generates different scene
展开原文
Ironically, Grok 4.6 works beautifully on Grok Build but has shit usage limits. It has more usage on Cursor but has inferior performance.
展开原文
I'm now using Grok 4.6 most of the time. Sonnet some times.
近 7 天暂时没有符合此筛选条件的精选评论。