Just did a round table review with the Grok @Bot engineering team.
Fixes are being implemented overnight and you should notice a dramatic improvement by tomorrow. If not, reply to this post and we will address any remaining issues right away.
One of many reasons, but this one was one of the biggest because it would spin up token usage talking between your grokbot agent and a cursor agent to push simple changes rather than just make them on its own for those of us who already had a nice workflow. Also, it forced everyone to burn tokens setting up an entire new workflow using the cursor cloud agent.
@MichaelHyatt@bot Was anyone denying this or calling people idiots? I think it was mostly unanimous that there was an issue with the grokbot agent capaiblites.
https://t.co/2HNG3FFfqp
There wasn't even a problem though. Even if they did change the default model. It was running fine. Waiting for Grok 4.8 seems silly. They changed what Grokbot was capable of and forced it to do all code changes through cursor cloud agents. This caused a massive issue with people's existing workflows.
https://t.co/t9ewJdZFkm
@Jtyles@grok@elonmusk Yeah bro. I canceled my subscription yesterday. The grokbot team says they're going to fix it. I'll give them one more chance if they do. But if something like this happens again, I'll have no choice but to leave this ecosystem forever.
This is great to see. Glad to hear this is potentially getting fixed. Why did the team remove the ability for the agents in Grokbot to push code changes to GitHub and deploy sites? I’m curious, what was the goal? It broke so many people’s basic workflows and caused unnecessary thrash between the bot and cursor cloud agents.