I can remember when Bill Gates said we would never need more than 640K RAM.
There will always be room for more technology.
I can remember when Bill Gates said we would never need more than 640K RAM.
There will always be room for more technology.
original link (archive.ph)
OpenAI researchers point to insufficient high-quality training data as one reason for the slowdown. Most publicly available texts and data have already been used. In response, OpenAI created a "Foundations Team" led by Nick Ryder, The Information reports.
This aligns with CEO Sam Altman's statement in June that while data exists in sufficient quantities, the focus will shift to learning more from less data. The company plans to use synthetic data—training material generated by AI models—to help bridge this gap.
I predicted this months ago. By then they must have already trained these AI engines on almost every publicly available line of code to be found. Even if they did train them with more unfiltered code it likely would not improve them. Even if they paid skilled programmers to filter the mediocre code out of the training data, or they actually got the AI to generate its own high quality training data, it would not suddenly make the AI intelligent.
Unless there is a breakthrough with the current generation of AIs this is as good as they will get. They have plateaued.
That doesn’t mean they are useless. They are great for looking up a method to do a specific task. Beyond that, you need to be able to program because these tools cannot do it for you.
[original link](https://archive.ph/3BJ86)
> OpenAI researchers point to insufficient high-quality training data as one reason for the slowdown. Most publicly available texts and data have already been used. In response, OpenAI created a "Foundations Team" led by Nick Ryder, The Information reports.
>
> This aligns with CEO Sam Altman's statement in June that while data exists in sufficient quantities, the focus will shift to learning more from less data. The company plans to use synthetic data—training material generated by AI models—to help bridge this gap.
I predicted this months ago. By then they must have already trained these AI engines on almost every publicly available line of code to be found. Even if they did train them with more unfiltered code it likely would not improve them. Even if they paid skilled programmers to filter the mediocre code out of the training data, or they actually got the AI to generate its own high quality training data, it would not suddenly make the AI intelligent.
Unless there is a breakthrough with the current generation of AIs this is as good as they will get. They have plateaued.
That doesn’t mean they are useless. They are great for looking up a method to do a specific task. Beyond that, you need to be able to program because these tools cannot do it for you.
You are currently inside a comment thread.
Click here to see all the comments (1).