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

371–380 of 433 posts

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

#371

Post by accrual »

mhitza wrote: post #275
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 often use ChatGPT without an account and ChatGPT 5 mini (which you get while logged out) might as well be Mistral 7b + web search. Its that mediocre. Even the original 3.5 was way ahead.

I kinda miss the original 3.5 model sometimes. Definitely not as smart as 4o but wow was it impressive when new. Apparently I have a very early ChatGPT account per the recent "wrapped" feature.

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

#372

Post by achierius »

marrone12 wrote: post #104
make3 wrote: post #88

Earlier quoted context omitted.

Your work exploits people's addictive propensity and behaviours, and gives corporations incentives and tools to build on that. Insane spin you're putting on it. At best, you're a cog in one of the worst recent evolutions of capitalism.

Advertising is not a recent evolution of capitalism, it's a foundational piece of it. Whatever you do as a job would not exist if there was no one marketing it. This hostility seems insane.

> Advertising is not a recent evolution of capitalism, it's a foundational piece of it

What does that say about capitalism?

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

#373

Post by runarberg »

fc417fc802 wrote: post #365
runarberg wrote: post #344

Earlier quoted context omitted.

> It is entirely reasonable to wonder how that might extrapolate to other addictive activities. I presume my GP would have no objections to regulating these things their commenter whatabouted. The inconsistency is with the legislator, not in GPs arguments.

Obviously I also think the commenter would support that - I said as much in GP. In context, the reply is suggesting (implicitly) that it is an absurd stance to take. That it means being largely against the way our society is currently organized. That is not a whataboutism. Like if someone were to say "man we should really outlaw bikes, you can get seriously injured while using one" a reasonable response would be to p…

> a reasonable response would be to point out all the things that are more dangerous than bikes that the vast majority of people clearly do not want to outlaw.

I disagree. It is in fact not a reasonable argument, it is not even a good argument. It is still whataboutism. There are way better arguments out there, for example:

Bicycles are in fact regulated, and if anything these regulations are too lax, as most legislators are categorizing unambiguous electric motorcycles as bicycles, allowing e-motorcycle makers to market them to kids and teenagers that should not be riding them.

Now as for the whatabout cars argument: If you compare car injuries to bicycle injuries, the former are of a completely different nature, by far most bicycle injuries will heal, that is not true of car injuries (especially car injuries involving a victim on a bicycle). So talking about other things that are more dangerous is playing into your opponents arguments, when there is in fact no reason to do that.

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

#375

Post by fc417fc802 »

palmotea wrote: post #353
fc417fc802 wrote: post #339

Earlier quoted context omitted.

I don't object to alcohol being tolerated. But I do think that distinguishing it from other drugs is odd. Particularly when the primary reason given for regulating other drugs is their addictiveness which alcohol shares. We tolerate a recreational drug. Lots of people regularly consume a recreational drug and yet somehow society doesn't split at the seams. We should just acknowledge the reality. I think people would…

> I don't object to alcohol being tolerated. But I do think that distinguishing it from other drugs is odd. The point I was making is that it's not odd, unless you're thinking about human culture wrong (e.g. like its somehow weird that broad rules have exceptions). > Particularly when the primary reason given for regulating other drugs is their addictiveness which alcohol shares. One, not all addictive drugs are equa…

No? I don't never said (and don't believe) any of that. I don't think the legislative inconsistency is odd. As you rightly point out it's perfectly normal for rules to be inconsistent due to (among other things) shared culture. The former exists to serve the latter after all, not the other way around.

What I said I find odd is the way people refuse to plainly call alcohol what it is. You can refer to it as a drug yet still support it being legal. The cognitive inconsistency (ie the refusal to admit that it is a drug) is what I find odd.

I also find it odd that we treat substances that the data clearly indicates are less harmful than alcohol as though they were worse. We have alcohol staring us in the face as a counterexample to the claim that such laws are necessary. I think that avoidance of this observation can largely explain the apparent widespread unwillingness to refer to alcohol as a drug.

> One, not all addictive drugs are equally addictive.

Indeed. Alcohol happens to be more addictive than most substances that are regulated on the basis of being addictive. Not all, but most. Interesting, isn't it?

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

#376

Post by fragmede »

palmotea wrote: post #356
noosphr wrote: post #189

Earlier quoted context omitted.

The Politician's syllogism in action: That is terrible. Se have to do something. This is something. We must do it. It terms of harm current laws on drugs fail everyone but teetotaller who want everyone else to have a miserable life too.

> It terms of harm current laws on drugs fail everyone but teetotaller who want everyone else to have a miserable life too. You think teetotallers have miserables lives? Come on.

There's a conservation of excitement for each human. If someone's life was exciting but then it got boring, unless they do a shit ton of work on themselves, they're gonna have to find that excitement somehow. We see this with Hollywood actresses who shoplift when they have more than enough money to buy the things they stole.

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

#377

Post by djsavvy »

toxic72 wrote: post #112
europeanNyan wrote: post #86

After they pushed the limits on the Thinking models to 3000 per week, I haven't touched anything else. I am really satisfied with their performance and the 200k context windows is quite nice. I've been using Gemini exclusively for the 1 million token context window, but went back to ChatGPT after the raise of the limits and created a Project system for myself which allows me to have much better organization with Proj…

I REALLY struggle with Gemini 3 Pro refusing to perform web searches / getting combative with the current date. Ironically their flash model seems much more likely to opt for web search for info validation. Not sure if others have seen this... I could attribute it to: 1. It's known quantity with the pro models (I recall that the pro/thinking models from most providers were not immediately equipped with web search too…

I was seeing this several weeks ago but seems fixed recently, at least for my types of queries. I only use Pro

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

#379

Post by fc417fc802 »

runarberg wrote: post #373
fc417fc802 wrote: post #365

Earlier quoted context omitted.

Obviously I also think the commenter would support that - I said as much in GP. In context, the reply is suggesting (implicitly) that it is an absurd stance to take. That it means being largely against the way our society is currently organized. That is not a whataboutism. Like if someone were to say "man we should really outlaw bikes, you can get seriously injured while using one" a reasonable response would be to p…

> a reasonable response would be to point out all the things that are more dangerous than bikes that the vast majority of people clearly do not want to outlaw. I disagree. It is in fact not a reasonable argument, it is not even a good argument. It is still whataboutism. There are way better arguments out there, for example: Bicycles are in fact regulated, and if anything these regulations are too lax, as most legisla…

I believe you have a categorical misunderstanding of what "whataboutism" actually means.

If the point being made is "people don't generally agree with that position" it is by definition not whataboutism. To be whataboutism the point being made is _required_ to be nil. That is, the two things are not permitted to be related in a manner that is relevant to the issue being discussed.

Now you might well disagree with the point being made or the things being extrapolated from it. The key here is merely whether or not such a point exists to begin with. Observing that things are not usually done a certain way can be valid and relevant even if you yourself do not find the line of reasoning convincing in the end.

Contrast with my example about countries persecuting groups of people. In that case there is no relevant relation between the acts or the groups. That is whataboutism.

So too your earlier example involving human trafficking. The fact that enforcement is not always successful has no bearing (at least in and of itself) on whether or not we as a society wish to permit it.

BTW when I referred to danger there it wasn't about cars. I had in mind other recreational activities such as roller blading, skateboarding, etc. Anything done for sport that carries a non-negligible risk of serious injury when things go wrong. I agree that it's not a good argument. It was never meant to be.

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

#380

Post by SomeUserName432 »

I actually tried GPT 4.1 for the first time a few hours ago(1).

I spent about half an hour trying to coax it in "plan mode" in IntelliJ, and it kept spitting out these generic ideas of what it was going to do, not really planning at all.

And when I asked it to execute the plan.. it just created some generic DTO and said "now all that remains is ".

Absolutely worst experience with an AI agent so far, not to say that my overall experience has been terrific.

1) Our plan for Claude Opus 4.5 "ran out" or something.

Post reply on HN