Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

openai.com

Post reply on HN
Print view View original

311–320 of 433 posts

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#311

Post by mFixman »

azuanrb wrote: post #278

It’s interesting that many comments mention switching back to Claude. I’m on the opposite end, as I’ve been quite happy with ChatGPT recently. Anthropic clearly changed something after December last year. My Pro plan is barely usable now, even when using only Sonnet. I frequently hit the weekly limit, which never happened before. In contrast, ChatGPT has been very generous with usage on their plan. Another pattern I’…

I've been impressed by how good ChatGPT is at getting the right context old conversations.

When I ask simple programming questions in a new conversation it can generally figure out which project I'm going to apply it to, and write examples catered to those projects. I feel that it also makes the responses a bit more warm and personal.

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#312

Post by Angostura »

Hard_Space wrote: post #251
QuadrupleA wrote: post #247

Been unhappy with the GPT5 series, after daily driving 4.x for ages (I chat with them through the API) - very pedantic, goes off on too many side topics, stops following system instructions after a few turns (e.g. "you respond in 1-3 sentences" becomes long bulleted lists and multiple paragraphs very quickly. Much better feel with the Claude 4.5 series, for both chat and coding.

> you respond in 1-3 sentences" becomes long bulleted lists and multiple paragraphs very quickly This is why my heart sank this morning. I have spent over a year training 4.0 to just about be helpful enough to get me an extra 1-2 hours a day of productivity. From experimentation, I can see no hope of reproducing that with 5x, and even 5x admits as much to me, when I discussed it with them today: > Prolixity is a side…

And how would GPT 5.0 know that, I wonder. I bet it’s just making stuff up.

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#313

Post by spprashant »

QuadrupleA wrote: post #247

Been unhappy with the GPT5 series, after daily driving 4.x for ages (I chat with them through the API) - very pedantic, goes off on too many side topics, stops following system instructions after a few turns (e.g. "you respond in 1-3 sentences" becomes long bulleted lists and multiple paragraphs very quickly. Much better feel with the Claude 4.5 series, for both chat and coding.

I can never understand why it is so eager to generate walls of text. I have instructions to always keep the response precise and to the point. It almost seem like it wants to overwhelm you, so you give up and do your own research.

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#314

Post by anarticle »

QuadrupleA wrote: post #247

Been unhappy with the GPT5 series, after daily driving 4.x for ages (I chat with them through the API) - very pedantic, goes off on too many side topics, stops following system instructions after a few turns (e.g. "you respond in 1-3 sentences" becomes long bulleted lists and multiple paragraphs very quickly. Much better feel with the Claude 4.5 series, for both chat and coding.

I also found this disturbing, as I used to use GPT for small worked out theoretical problems. In 5.2, the long list of repeated bulleted lists and fortune cookies was a negative for my use case. I replaced some of that use with Claude and am experimenting with LM studio and gpt-oss. It seemed like an obvious regression to me, but maybe people weren't using it that way.

For instance something simple like: "If I put 10kw in solar on my roof when is the payback given xyz price / incentive / usage pattern."

Used to give a kind of short technical report, now it's a long list of bullets and a very paternalistic "this will never work" kind of negativity. I'm assuming this is the anti-sycophant at work, but when you're working a problem you have to be optimistic until you get your answer.

For me this usage was a few times a day for ideas, or working through small problems. For code I've been Claude for at least a year, it just works.

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#315

Post by rolymath »

5o1ecist wrote: post #217
jacquesm wrote: post #201

Earlier quoted context omitted.

All of the things above were driven by porn, that can be proven. The AI stuff in the generic sense is not but you can bet that someone somewhere right now is working on improving photo realism of hair, eyes and skintone and they're not doing that to be able to make the next installment of little red riding hood.

[flagged]

[flagged]

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#316

Post by hxugufjfjf »

fullstackchris wrote: post #286
azuanrb wrote: post #278

It’s interesting that many comments mention switching back to Claude. I’m on the opposite end, as I’ve been quite happy with ChatGPT recently. Anthropic clearly changed something after December last year. My Pro plan is barely usable now, even when using only Sonnet. I frequently hit the weekly limit, which never happened before. In contrast, ChatGPT has been very generous with usage on their plan. Another pattern I’…

This is incorrect. I have the $200 per year plan and use Opus 4.5 every day. Though granted it comes in ~4 hour blocks and it is quite easy to hit the limit if executing large tasks.

Four hours to be outdoors, walk the dog, drink coffee and talk to a friend outside a screen. Best part of my day.

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#317

Post by tl »

azuanrb wrote: post #278

It’s interesting that many comments mention switching back to Claude. I’m on the opposite end, as I’ve been quite happy with ChatGPT recently. Anthropic clearly changed something after December last year. My Pro plan is barely usable now, even when using only Sonnet. I frequently hit the weekly limit, which never happened before. In contrast, ChatGPT has been very generous with usage on their plan. Another pattern I’…

I have Claude whiplash right now. Anthropic bumped limits over the holidays to drive more usage. Which combined with Opus's higher token usage and weird oddities in usage reporting / capping (see sibling comments), makes me suspect they want to drive people from Pro -> Max without admitting it.

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#318

Post by ziml77 »

Hard_Space wrote: post #251
QuadrupleA wrote: post #247

Been unhappy with the GPT5 series, after daily driving 4.x for ages (I chat with them through the API) - very pedantic, goes off on too many side topics, stops following system instructions after a few turns (e.g. "you respond in 1-3 sentences" becomes long bulleted lists and multiple paragraphs very quickly. Much better feel with the Claude 4.5 series, for both chat and coding.

> you respond in 1-3 sentences" becomes long bulleted lists and multiple paragraphs very quickly This is why my heart sank this morning. I have spent over a year training 4.0 to just about be helpful enough to get me an extra 1-2 hours a day of productivity. From experimentation, I can see no hope of reproducing that with 5x, and even 5x admits as much to me, when I discussed it with them today: > Prolixity is a side…

What kind of "training" did you do?

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#319

Post by Kiboneu »

leumon wrote: post #73

> We’re continuing to make progress toward a version of ChatGPT designed for adults over 18, grounded in the principle of treating adults like adults, and expanding user choice and freedom within appropriate safeguards. To support this, we’ve rolled out age prediction for users under 18 in most markets. https://help.openai.com/en/articles/12652064-age-prediction-... interesting

How I think it could play out:

- OpenAI botches the job. Article pieces are written about the fact that kids are still able to use it.

- Sam “responds” by making it an option to use worldcoin orbs to authenticate. You buy it at the “register me” page, but you will get an equivalent amount of worldcoin at current rate. Afterwards the orb is like a badge that you can put on your shelf to show to your guests.

“We heard you loud and clear. That’s why we worked hard to provide worldcoin integration, so that users won’t have to verify their age through annoying, insecure and fallible means.” (an example marketing blurb would say, implicitly referring to their current identity servicer Persona which people find annoying).

- After enough orb hardware is out in the public, and after the api gains traction for 3rd parties to use it, send a notice that x months for now, login without the orb will not be possible. “Here is a link to the shop page to get your orb, available in colors silver and black.”

Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

#320

Post by PunchyHamster »

GoatInGrey wrote: post #131
leumon wrote: post #73

> We’re continuing to make progress toward a version of ChatGPT designed for adults over 18, grounded in the principle of treating adults like adults, and expanding user choice and freedom within appropriate safeguards. To support this, we’ve rolled out age prediction for users under 18 in most markets. https://help.openai.com/en/articles/12652064-age-prediction-... interesting

Pornographic use has long been the "break glass in case of emergency" for the LLM labs when it comes to finances. My personal opinion is that while smut won't hurt anyone in of itself, LLM smut will have weird and generally negative consequences. As it will be crafted specifically for you on top of the intermittent reinforcement component of LLM generation.

I guess technically it will make some onlyfans content creators unemployed, given there is pretty large market for custom sexual content there.
Post reply on HN