Do you customize or personalize these at all? Or use it just out of the box? I use gemini for image generation and as an, assistant through my android although not frequently. As a chat assistant the online Google UI is a turnoff personally.
For tone, I prefer efficient — higher signal-to-noise.
In custom instructions I’ll sometimes write something like “tell it like it is.” Interestingly, some models then start with “okay, I’ll tell you like it is…” which makes me wonder whether that’s psychological framing, operational behavior, or both.
Curious why you asked — have you found customization meaningfully changes performance?
Since I primarily used ChatGPT, I picked up a bunch of prompts from people sharing it in order to optimize for better results. I don't know if this is relevant anymore as I think they've fixed quite a bit and now you can customize tone and warmth directly.
My prompts were more on avoiding filler, be more direct etc, no emojis etc.
In my case, Instagram eventually got to a point where most of my friends and family stopped posting. And I started following more creators because their content was interesting. These days there are some a few people I follow who are friends and I mostly just send them dumb reels. I see it more as a platform to consume content than keeping up with updates.
That said, I go through cycles of removing the app and reinstalling it later because it gets addictive.
All of the Claude models are smarter than the GPT models. I had a few threads that I migrated from GPT to Claude and every single one Claude pointed out problems. Two examples:
1. In one, I was putting together a server build. Claude correctly pointed out some incompatibilities in some parts that GPT had recommended.
2. In another chat, I had asked for help interpreting lab results and suggesting supplements. Claude pointed out that GPT was over-interpreting the results and suggesting things that weren't backed up by facts.
I presented Claude's response back to GPT and in both of these specific cases, GPT admitted it was wrong and didn't have any rebuttal. It's hard to say without doing a more scientific experiment whether GPT is indeed worse, but anecdotally I find myself pointing out flaws in Claude's reasoning far less frequently than GPT, especially with Opus.
Another less important distinction: GPT has a very distinct writing style that heavily formats responses and repeats itself a few times. Claude is succinct and mostly writes like a person might. It's easier to talk to and feels less "cringe" and sycophantic.
ChatGPT swings between writing degenerate free use shit and telling you that you should wait until marriage. Lots of moralism to it, really tries to censor you and manipulate you, even in normal conversations. Generally smart and capable, but the whiny attitude gets old.
Grok has zero filter, but is dumber than the others. Definitely built around cheapness. Caps answers at about 2500 words at most. Can be very funny because it will go along with anything.
Gemini sells all your data and doesn’t seem to have much of note. Offers some nice formatting options.
Claude is business focused so it won’t do anything degenerate, but its answers in general aren’t whiny. It might not do something, but it doesn’t attack you with morality.
Claude does not cap answer length and will do whatever needs doing. Their pricing is based around true usage, not message quantities, so it’ll write a mega message if it needs to.
It has the best memory implementation, combining both memories and RAG of your chat history. Projects have their own independent memories and RAG.
Claude code is ridiculously capable. In a few hours I produced something which would have taken months and £50,000 at least to produce.
Thanks, I'll try more of Claude. Back in the day when I first tried it out I easily burned through message limits every day. I've been mulling over paying for Claude Code but I just keep using the free tier of Antigravity and some from my Pro plan.
I happen to have a Gemini Pro subscription that I got through my network provider in India, but i use it only for coding and Nano Banana slop. And occasionally live audio/video chat from my mobile which is actually the best use case I've seen so far although it gets old pretty fast and isn't great beyond basic tasks.
I regularly (Say, once a month) do a comparison of results across all Claude, Gemini and ChatGPT. Just for reasons, not that I want to see if there's any benefit in changing.
It's not "fair" in that I pay for Claude [1] and not for the others, so models availability is not complete except for Claude.
So I did like things at time in the form of how they were presented, I came to really like Sonnet's "voice" a lot over the others.
Take into account Opus doesn't have the same voice, and I don't like it as much.
[1] I pay for the lower tier of their Max offering.
I had no idea this was a common thing lol. Can't imagine it where I grew up. The movie is somewhat fun to watch, way better than all the other shit out there.
reply