Haha, I also tested this out. I found that the same thing happened with GPT5 (with same tokens as o3). I didn’t test it so rigorously I can be confident, but might this mean GPT5-high = continued train of o3?
Also notable IMO that GPT-5 in the METR report is doing the new thing where it does ’ “ instead of actually saying a word (seemingly for various words) which o3 did not do.
Wanted ' ".
Ok.
But forging above ' ".
Ear illusions.
Better: We'll ' ".
Now final code steps:
5) After training we will Save the improved " ".
structures:
' ".
Now overshadow.
But the illusions of ' ".
Now to code.
But we must ensure to maintain optimizer ' ".
Ok.
Now sedation.
But we will maintain ' ".
Now Balanced.
I should have remembered, but I guess its the exact same evidence. Do you think that’s strong evidence gpt5 = continued train o3 + distillations?
Are there any models we have a lot of unfiltered CoTs for, distinct from OpenAI, which display the same dialect-shift? And do they use the same strange tokens?
I’ve only looked at deepseek and qwen cots, and they don’t have this strange way of talking.
Haha, I also tested this out. I found that the same thing happened with GPT5 (with same tokens as o3). I didn’t test it so rigorously I can be confident, but might this mean GPT5-high = continued train of o3?
Note that many of these same weird tokens have been observed in GPT-5 chains-of-thought (at least “marinade”, “illusions”, “overshadow”).
Also notable IMO that GPT-5 in the METR report is doing the new thing where it does
’ “instead of actually saying a word (seemingly for various words) which o3 did not do.I should have remembered, but I guess its the exact same evidence. Do you think that’s strong evidence gpt5 = continued train o3 + distillations?
Are there any models we have a lot of unfiltered CoTs for, distinct from OpenAI, which display the same dialect-shift? And do they use the same strange tokens?
I’ve only looked at deepseek and qwen cots, and they don’t have this strange way of talking.