Posted by atgctg 12/11/2025
System card: https://cdn.openai.com/pdf/3a4153c8-c748-4b71-8e31-aecbde944...
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.
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.
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.
The $100/hr is worth it for US programming jobs, but nothing else
Their best market might just be as a better Google with ads
I don't think marketing emails are written enough to constitute the "bulk" of it, but writing in general seems to be
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.
Same query - what romanian football player won the premier league
update. Even instant returns correct result without problems
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.
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...