Comment by imron
9 hours ago
> My favorite part of the new Groks has been how they speak in plain english. I simply cannot stand Claudish.
Grok has its own feel too. It's not as bad as Claude, but one of the things that bugs me is that it is far too terse.
It regularly seems to come up with terms and descriptions for things in its chain of reasoning and then uses these terms in its output assuming you understand what it's talking about.
I find I often have to ask it to re-explain what it means.
It’s frustrating that we can’t see the “thinking” - it’s like we only have access to half the conversation.
Devin shows model thinking.
I’m pretty sure the big bois don’t do it because it would undermine “confidence”.
Seeing a model output “Oh I should just delete blah. Wait blah is a production service, I shouldn’t touch that. Maybe I can gain access to blah? Oh the aws cli isn’t signed in to blah. I see kubectl has access to blah though! Wait, I should ask user permission first.”
Yeaaaaah. Thinking tokens are fuckin’ wild.
Idk I feel like the more likely answer is to prevent distillation. Having the thinking is definitely better UX (oftentimes, I don’t know if Codex is just hanging, which it often does, or working in silence).
I doubt most users would look at them if they were available. More likely they don’t want to stream distillation material.
Running some models locally and seeing these thinking tokens was quite the experience. I never saw an LLM so "unsure" about virtually everything.
You can double click on the 'thinking' text and it will expand and you can read it. The problem is that it will often have multiple thinking/tool call sections and it can be a needle/haystack problem to find the one with the thinking you are interested in.
We don’t have access to the real reasoning text for most closed models these days, mostly due to distillation threats
Ah, but you CAN see the thinking if you are willing to risk your account being banned. You just have to expose a "tool" with a specially crafted definition.
> It regularly seems to come up with terms and descriptions for things in its chain of reasoning and then uses these terms in its output assuming you understand what it's talking about.
I’ve noticed Astra doing this a lot as well.
I just got DeepSeek V4.1 Flash on our Azure Foundry w/ Pi and I found its tone to be refreshing.
Separately have been using Grok 4.6 for a bit and it's also pretty concise.
I wonder how much of this is due to reliance on Twitter data. Or even just RLHF from humans that have a preference for Twitter style information.
I don't think it's twitter. My guess would be that it's been trained for conciseness as way to improve token efficiency in the same vein as caveman.
SpaceX is a defense contractor (I don't mean this in a bad way). When the whole DoD/Anthropic thing flared up, I can guarantee you that SpaceX.ai was the first company invited to take their place as DoD AI provider.
I suspect that they specifically train Grok to be able to work well with military personnel -- speaking the way they speak: brief, to the point, efficient communication. Personally I really like this. Claude sounds like some demented clown from the marketing department.
I like communication that is brief and to the point. The problem is when it is so brief that the point isn't conveyed well.
[dead]
> it is far too terse
Anecdotally, I have noticed the same in the past week. It might just be anecdotal or driven by a long context window.