Many users praised Grok 4.5's persistence in the GitHub repo audit evaluation as a key advantage over GPT-5.5 for building capable autonomous agents.
Based on 222 visible X reactions from 750 accounts.
Ask a question below.
Published answers will appear here.
@elonmusk *_"Grok 4.5 with that dogged energy 😤 Most persistent agent model tested vs GPT-5.5 and GLM-5.2. Love to see it 'Doesn't give up' is exactly what you want in an agent"_*
@elonmusk That persistence is exactly what separates basic chatbots from actual autonomous agents. Huge win for Grok 4.5
@elonmusk Grok constantly lies to me about Jews and covers up their crimes. Please fix this and stop being a nigger
@elonmusk This Grok 4.5 is absolutely impressive. What a turnaround.
Many users praised Grok 4.5's persistence in the GitHub repo audit evaluation as a key advantage over GPT-5.5 for building capable autonomous agents.
Based on 222 visible X reactions from 750 accounts.
Ask a question below.
Published answers will appear here.
Grok doesn’t give up https://twitter.com/composio/status/2075225191160889786