Top
Best
New

Posted by atgctg 12/11/2025

GPT-5.2(openai.com)
https://platform.openai.com/docs/guides/latest-model

System card: https://cdn.openai.com/pdf/3a4153c8-c748-4b71-8e31-aecbde944...

1195 points | 1083 commentspage 8
jrflowers 12/11/2025|
OpenAI is really good at just saying stuff on the internet.

I love the way they talk about incorrect responses:

> Errors were detected by other models, which may make errors themselves. Claim-level error rates are far lower than response-level error rates, as most responses contain many claims.

“These numbers might be wrong because they were made up by other models, which we will not elaborate on, also these numbers are much higher by a metric that reflects how people use the product, which we will not be sharing“

I also really love the graph where they drew a line at “wrong half of the time” and labeled it ‘Expert-Level’.

10/10, reading this post is experientially identical to watching that 12 hours of jingling keys video, which is hard to pull off for a blog.

namesbc 12/12/2025||
So the rosy biased estimate is OpenAI is saving 1 hour of work per day, so 5 hours total per-work week and 20 hours total per-month.

With a subsidized cost of $200/month for OpenAI it would be cheaper to hirer a part-time minimum wage worker than it would be to contract with OpenAI.

And that is the rosiest estimate OpenAI has.

maerch 12/12/2025||
The closest I come to working with part-time, minimum-wage workers is working with student employees. Even then, they earn more and usually work more than five hours a week.

Most of the time, I end up putting in more work than I get out of it. Onboarding, reviewing, and mentoring all take significant time.

Even with the best students we had, paying around 400 euros a month, I would not say that I saved five hours a week.

And even when they reach the point of being truly productive, they are usually already finished with their studies. If we then hire them full-time, they cost significantly more.

dangoodmanUT 12/12/2025|||
A part time minimum wage worker can't code
namesbc 12/12/2025||
Check the wages of coders outside of the US
6510 12/13/2025||
There use to be a mythological creature on irc from south America (sorry forgot the specifics) who was both a 10x dev and a 10x mathematician. One day he showed a picture of his computer. It was a low end laptop with a tft monitor and an external keyboard because the screen and the keyboard didn't work. It explained everything, the machine was just good enough to write code, do math, read stack exchange and lurk irc with his ghosts.
namesbc 12/12/2025|||
It you take of the rosy glasses, it is more like 10 hours saved per-month at an unsubsidized cost of $1000/month

The $100/hr is worth it for US programming jobs, but nothing else

AstroBen 12/12/2025||
What people here forget is coding is a tiny minority of the actual usage. ~5% if I remember correctly?

Their best market might just be as a better Google with ads

namesbc 12/12/2025|||
Yep, bulk of AI usage is generating marketing emails
AstroBen 12/12/2025||
Here's OpenAI's data on it: https://www.nber.org/system/files/working_papers/w34255/w342...

I don't think marketing emails are written enough to constitute the "bulk" of it, but writing in general seems to be

YouAreWRONGtoo 12/12/2025|||
[dead]
ofermend 12/12/2025||
GPT-5.2 just added to Vectara Hallucination Leaderboard. Definitely an improvement over GPT-5.1 - congrats to the team

https://github.com/vectara/hallucination-leaderboard

sundarurfriend 12/11/2025||
> new context management using compaction.

Nice! This was one of the more "manual" LLM management things to remember to regularly do, if I wanted to avoid it losing important context over long conversations. If this works well, this would be a significant step up in usability for me.

0xdeafbeef 12/11/2025||
much better https://chatgpt.com/s/t_693b489d5a8881918b723670eaca5734 than 5.1 https://chatgpt.com/s/t_6915c8bd1c80819183a54cd144b55eb2.

Same query - what romanian football player won the premier league

update. Even instant returns correct result without problems

https://chatgpt.com/s/t_693b49e8f5808191a954421822c3bd0d

dandiep 12/11/2025||
Still no GPT 5.x fine tuning?

I emailed support a while back to see if there was an early access program (99.99% sure the answer is yes). This is when I discovered that their support is 100% done by AI and there is no way to escalate a case to a human.

jazzyjackson 12/11/2025|
Containment breach is going to occur from a disgruntled customer convincing the customer service bot it needs to get a hold of a supervisor
dandiep 12/11/2025||
I tried this!

Me: Is it possible get early access to the GPT 5 fine tuning? It is much better at non-English languages, which is the majority of what we do, so it would be greatly beneficial to us.

Bot: I'm an AI support agent. I don't have information about early access to GPT-5 fine-tuning or unannounced features. Currently, there is no public information or program for early access to GPT-5 fine-tuning. Please keep an eye on official OpenAI channels for updates. Let me know if you have any questions about current features or products!

Me: Can you ask someone from the team if I can be part of the early access? I know there is no public information, but there is an early access program and I would like to be part of it.

Bot: I'm an AI support agent and do not have the ability to forward requests or make inquiries about early access programs with the OpenAI team. If early access becomes available, it will be announced through official channels. Let me know if you have any other questions about OpenAI products or current fine-tuning options.

Me: How do I get in touch with the open ai team?

Bot: I'm an AI support agent and can only assist with OpenAI products or services through this support channel. There is no separate contact method for the OpenAI team beyond official support and public announcements. If you have questions about current products or features, I'm here to help

Should have tried a jailbreak maybe...

jazzyjackson 12/11/2025||
Yea you might have to convince it someone is in mortal danger or something
int_19h 12/12/2025||
You're talking about a model that will notoriously refuse to say a racist word even if you tell it that it's the only way to prevent a nuclear apocalypse.
gkbrk 12/11/2025||
Is this the "Garlic" model people have been hyping? Or are we not there yet?
0x457 12/11/2025|
Garlic will be released 2026Q1.
kachapopopow 12/11/2025||
did they just tune the parameters? the hallucinations are crazy high on this version.
johnsutor 12/11/2025|
https://platform.openai.com/docs/models/gpt-5.2 More information on the price, context window, etc.
More comments...