Gemini, Claude, ChatGPT or whatever. Can we all agree, that it's great to have so much choice?
You’re absolutely right!
Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
321–330 of 433 posts
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#322It’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.
ChatGPT having memory of previous conversations is very confusing.
Occasionally it will pop up saying "memory updated!" when you tell it some sort of fact. But hardly ever. And you can go through the memories and delete them if you want.
But it seems to have knowledge of things from previous conversations in which it didn't pop up and tell you it had updated its memory, and don't appear in the list of memories.
So... how is it remembering previous conversations? There is obviously a second type of memory that they keep kind of secret.
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#323Earlier quoted context omitted.
Not having my job would be a tiny price to pay compared to the benefit of living in a world with no advertisements.
“No advertisements” seems extreme to me. I want to know when a good band is playing at a local venue, or has an album out. I like hearing about new books, or a restaurant near me. The absolutist position that “all ads are always bad” is a non-starter for me. Especially as long as we exist in a capitalist system. Small business, indie creators, etc. must advertise in some fashion to survive. It’s only the behemoths th…
There are (and continue to be) millions of young people who do not yet have firm preferences. For the already faithful, their advertising is mostly about reminding them to consume more.
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#324Earlier quoted context omitted.
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.
ChatGPT having memory of previous conversations is very confusing. Occasionally it will pop up saying "memory updated!" when you tell it some sort of fact. But hardly ever. And you can go through the memories and delete them if you want. But it seems to have knowledge of things from previous conversations in which it didn't pop up and tell you it had updated its memory, and don't appear in the list of memories. So...…
If you go to Settings -> Personalisation -> Memory, you have two separate toggles for "Reference saved memories" and "Reference chat history".
The first one refers to the "memory updated" pop-up and its bespoke list of memories; the second one likely refers to some RAG systems for ChatGPT to get relevant snippets of previous conversations.
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#325> 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.
For those interested in smut I'd recommend to use local Mistral models.
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#326It’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.
Agreed that it can work well, but it can also irritating - I find myself using private conversations to attempt to isolate them, a straightforward per-chat toggle for memory use would be nice.
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#327Earlier quoted context omitted.
I want smut that talks about agent based development and crawdbot to do dirty dirty things. Does that exist yet. I don't think so.
Best I can do is [1] Sentient Lesbian Em-Dashes and [2] An AI hallucination made real for now. The man's probably thinking something up though. "Pounded in the butt by Microslop Agentic Studio 2026" has a ring. [1] https://www.amazon.com/Sentient-Lesbian-Em-Dash-Punctuation-... [2] https://www.amazon.com/Last-Algorithm-Pounded-Claimed-Sun-Ti...
> Sentient Lesbian Em-Dashes
Looked at the cover and saw “From Two Time Hugo Award Finalist Chuck Tingle”.
There’s no way that’s true. But I did a quick search anyway, and holy shit!
https://www.thehugoawards.org/hugo-history/2016-hugo-awards/...
https://www.thehugoawards.org/hugo-history/2017-hugo-awards/...
The story behind it:
https://www.quora.com/How-did-Chuck-Tingle-become-a-Hugo-Awa...
https://archive.ph/20160526154656/http://www.vox.com/2016/5/...
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#328What about the Advanced Voice feature, has this been updated to 5.x models yet?
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#329It’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’…
Well, claude at least was successful in getting me to pay. It became utterly annoying that I would hit the limit just with a couple of follow ups to my long running discussion and made me wait for a few hours.
So it worked, but I didn't happily pay. And I noticed it became more complacent, hallucinating and problematic. I might consider trying out ChatGPTs newer models again. Coding and technical projects didn't feel like its stronghold. Maybe things have changed.
Re: Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT
#330Earlier quoted context omitted.
I was using whataboutism to demonstrate how bad of an argument whataboutism is. My arguments were exactly as bad as my parent’s, and that was the point.
Pointing out an inconsistency isn't always whataboutism (and I don't think it was in this case). An implied argument was made that we should regulate LLMs for the same reason that we regulate drugs (presumably addiction, original commenter wasn't entirely clear). It is entirely reasonable to wonder how that might extrapolate to other addictive activities. In fact we currently regulate those quite differently than dru…
> including the part where alcohol isn't considered to be a drug for some strange reason.
It's not a strange reason. IIRC, most cultures have a culturally understood and tolerated intoxicant. In our culture, that's alcohol.
Human culture is not some strange robotic thing, where the expectation is some kind hyper consistency in whatever narrow slice you look at.