Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
IMG_0485.jpeg


It’s confused as to who it is.
 
It can hit or miss with all of them. I've had good success with Perplexity as a search engine. Claude seems to get to "know you" better for more personal queries.
 
I'm not sure why OpenAI would switch all users to the 4.1 model, much less the mini version, since the "o" in "4o" stands for "omni", meaning it can take not just text as input, but also images and audio (but not video yet), and it can also include images in its responses (the other two can't), and it has a more conversational style. But maybe it's that more conversational style that OpenAI wants to get away from, or just keep it as a non-default option, after the debacle with the 4o model's flamboyantly unctuous responses that ended about a week ago when OpenAI "adjusted" that approach when people couldn't stand it.

I just asked the 4o model to compare all three models. It said:

• GPT-4.1-mini is like a very smart intern—quick, cost-efficient, and competent in most general tasks, but not as deep or nuanced as the larger models.

• GPT-4.1 is the analytical specialist—great for complex reasoning, but slower and less adaptable.

• GPT-4o is the conversational polymath—fast, expressive, and capable of working across text, images, and audio.


ChatGPT also says about its 4o model: "It's slightly more interpretive than strictly factual." If this means less nonsense and hallucinations with the other two top models, the better.
 
Last edited:
Yep, Chat-GPT just put another 2.5 years between it and Apple's non-existent AI. It seems that every month that goes by Apple falls further and further behind. I mean I guess trying to Siri from 2010 to 2016 is a monumental task, but Apple will not win any races by taking 2 years to advance 1 year. Maybe Apple should outsource AI development to some other 3rd world country. It might speed up things.
 
I’m so surprised by the number of people who are happy with ChatGPT. These past few weeks, I don’t think I’ve had a single correct answer from it, even for the simplest questions. It doesn’t take my settings into account, it hallucinates answers, it makes completely false statements, and it’s been totally unusable to the point that I cancelled my subscription. I had to ask it to check its answers every time, and every time I would get “You’re right, I made a mistake,” literally every single time. Even the translations were completely off (I’m French, I understand English perfectly but I’m not very good with grammar). Once it even translated into German....
So it is at least as good as most politicians. Good to know.
 
I literally asked it which model to use for my needs and recommended the pros and cons... So I feel you can just do this to answer your comments (spoiler alert: 4.1 was the best and more accurate, especially with the newly expanded token limit).
Ah, but which model did you ask? because maybe 4o-mini is "great at recommending another model."
 
Using ChatGPT to help plan with vacation itinerary, it's been fairly helpful. Specially as I have to plan to adjust travelling with a 2 year old toddler. Meanwhile, Siri can't even tell me the weather for tomorrow.
 
I'm not sure why OpenAI would switch all users to the 4.1 model, much less the mini version, since the "o" in "4o" stands for "omni", meaning it can take not just text as input, but also images and audio (but not video yet), and it can also include images in its responses (the other two can't), and it has a more conversational style. But maybe it's that more conversational style that OpenAI wants to get away from, or just keep it as a non-default option, after the debacle with the 4o model's flamboyantly unctuous responses that ended about a week ago when OpenAI "adjusted" that approach when people couldn't stand it.
I could confirm that GPT-4.1 can analyse images very well, and it can start the process of generating images. ChatGPT actually uses a different model named "GPT Image 1" to generate images.
 
  • Like
Reactions: johnsawyercjs
View attachment 2511038

It’s confused as to who it is.
I have this version


NB: FREE version




==================


Hi! 👋 I’m ChatGPT, currently running on GPT-4-turbo, which is a faster and more efficient variant of GPT-4 developed by OpenAI.








What does that mean for you?








  • 🖼️ I can understand both text and images — you can upload pictures, and I can help analyze or explain them.
  • 🧠 My training includes knowledge up to June 2024.
  • 🌐 I can also search the web (when needed) to provide fresh, real-time information.
  • 💬 I’m designed to handle long, thoughtful conversations smoothly and quickly.
  • 🌍 I speak multiple languages fluently — including English, Romanian, Spanish, and many more.
















🔍 Key Differences: GPT-4 vs GPT-4-turbo





FeatureGPT-4GPT-4-turbo
SpeedSlowerFaster 🚀
Cost (to use via API)More expensiveCheaper 💸
EfficiencyStandardMore optimized ⚙️
Context lengthUp to 8K tokens (some 32K)Up to 128K tokens 🧠
Availability in ChatGPTNot usedUsed in ChatGPT (pro) ✅

Tokens = chunks of words I can remember in a conversation. More tokens = longer memory per interaction.










Also mine is not confused at all.

Yours is broken 🤣🤣🤣


Apple ID is based in the uk.
Realistically! real IP address
 
I’m so surprised by the number of people who are happy with ChatGPT. These past few weeks, I don’t think I’ve had a single correct answer from it, even for the simplest questions.

1747468764957.png


Maybe your questions weren't simple enough?
 
I could confirm that GPT-4.1 can analyse images very well, and it can start the process of generating images. ChatGPT actually uses a different model named "GPT Image 1" to generate images.
Interesting. I asked 4o if its 4.1 models could analyze images sent to it by the user, and generate images too, and it said no to both. Though I'm not surprised--I've asked ChatGPT various questions about itself over the past year or so, and sometimes it gets its replies wrong.
 
Seems to have gotten dumber on a Plus plan in my case - (re)tried with extra prompting engineering effort on both 4.1 and 4.5 respectively.
 
In my experience, Gemini is much better than ChatGPT.
Fr?

Re Gemini I asked medical advice >> always prompts me to go to a doctor.

ChatGPT sorted a lot of small issues I have. AGAIN tried and tested and all worked

Saved a lot of trips to my gp and physiotherapist 🤣🤣🤣
 
  • Wow
Reactions: gusmula
What an awful naming convention. Is 4.1 supposed to be better than 4o? You know your naming convention is bad when even Google has a better handle on theirs.
 
Seriously. It feels like they need to do a hard reset on the naming/versioning. I have a plus subscription, and it's still defaulting to 4o, with o3, o4-mini, and o4-mini-high as the main alternate choices. You have to go under "More Models" to find 4.1, 4.1-mini, and 4.5. I would love to assume that 4.5 is the latest greatest new hotness, but honestly I wouldn't put $100 on that bet. Is 4o better than o3? is o less than 1? or is it 15, since it's the letter "o"? why would I choose 4.1-mini over 4.1? Why would I use anything except 4.5? Does 4.5 have the same "advanced reasoning" as o3? 4.1 is for "quick coding", but o4-mini-high is "great at coding"... so I need to choose between quick and great code? Is there a model that does great quick code?

And biggest question of all, does any of this matter? If the latest version is more or less all the improvements of the previous versions all wrapped up in one, then why give all this choice? Conversely, if all these choices are all meaningful, then why is there virtually no guidance on when to use which one?

Ask these questions to ChatGPT, it will be happy to explain the advantages of each model.
 
Ask these questions to ChatGPT, it will be happy to explain the advantages of each model.
I have, and it's answers are all over the place and change. Once I asked 4.1, and it told me that 4o was the latest... all the while 4.5 is staring at me from the drop down.

Even when it's right, you won't really get a clear explanation of the differences, which I partially suspect is because there's not always clear reasons why they differ in this way or that.
 
Nearly a month after this article and I’m still waiting for 4.1 to be default… 🤣 I have to change it every time.
It's weird. The mac app always defaults to 4o. The iphone app used to keep 4.1 selected for days or weeks, but I've noticed recently that it seems to revert back to 4o much more readily. I haven't used the web version for a long time, so I'm not sure there.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.