"Erdos problem #728 was solved more or less autonomously by AI"

Re:"Erdos problem #728 was solved more or less autonomously ... by sothatsit on Friday January 09, 2026 @09:42PM (#46562233)

This often feels like an annoying question to ask, but what models were you using?

The difference between free ChatGPT, GPT-5.2 Thinking, and GPT-5.2 Pro is enormous for areas like logic and math. Often the answer to bad results is just to use a better model.

Additionally, sometimes when I get bad results I just ask the question again with a slightly rephrased prompt. Often this is enough to nudge the models in the right direction (and perhaps get a luckier response in the process). However, if you are just looking at a link to a chat transcript, this may not be clear.

[ Parent | on HN ]

Re:"Erdos problem #728 was solved more or less autonomously ... by abdullahkhalids on Saturday January 10, 2026 @12:11AM (#46562980)

I have openrouter account, so I try different models easily. I have tried Sonnet, Opus, various versions of GPT, Deepseek. There are certainly differences in the quality. I also do rephrase prompts all the time. But ultimately, I can't quite get them to work in quantum computing. Far easier to get them to answer coding or writing related questions.

[ Parent | on HN ]

Re:"Erdos problem #728 was solved more or less autonomously ... by sothatsit on Sunday January 11, 2026 @04:35AM (#46574005)

Both Erdos #728 and #729 were solved with the use of GPT-5.2 Pro. Lesser models have much worse performance on difficult problems like these.

[ Parent | on HN ]