Screenshot of this question was making the rounds last week. But this article covers testing against all the well-known models out there.
Also includes outtakes on the ‘reasoning’ models.
Screenshot of this question was making the rounds last week. But this article covers testing against all the well-known models out there.
Also includes outtakes on the ‘reasoning’ models.
It’s overhyped in many areas, but it is undeniably improving. The real question is: will it “snowball” by improving itself in a positive feedback loop? If it does, how much snow covered slope is in front of it for it to roll down?
I think its far more likely to degrade itself in a feedback loop.
It’s already happening. GPT 5.2 is noticeably worse than previous versions.
It’s called model collapse.
To clarify : model collapse is a hypothetical phenomenon that has only been observed in toy models under extreme circumstances. This is not related in any way to what is happening at OpenAI.
OpenAI made a bunch of choices in their product design which basically boil down to “what if we used a cheaper, dumber model to reply to you once in a while”.
I feel that a lot of what is improving in the recent batch of model releases is the vetting of their training data - basically the opposite of model collapse.
Nothing requires an LLM to train on the entire internet.
That’s an excellent point! On that topic I recently listened to an interview of the founder of EleutherAI, who focuses on training small language models. She said they were able to train a 1B parameters reasoning model with 50K Wikipedia articles and carefully curated RL traces. The thing could run in your smartphone and is at parity with much larger models trained on trillions of tokens.
She also scoffed at Common Crawl and said it contained mostly cookies and porn. She had a kind of attitude like “no wonder the big labs need to slurp trillions of tokens when the tokens are such low quality”. Very interesting approach, if you understand french I can only recommend the interview.
The very interesting part will be how successful they are at training the training data selectors to choose high quality data sources.
I think a lot of it is still done by hand, and there is also synthetic data distilled from larger models of course.