It’s that they are trying to use statistics to encode entire thought processes into hidden variables from conversation snippets. They want to use statistics to go from many individual interactions to a large model, and then use that model to predict individual interactions again.
Has it been shown that the human brain doesn’t model the world in a similar way, though? A huge portion of human knowledge is both stored and transmitted in the form of language. Lots of human knowledge also follows the garbage in, garbage out theory, where you can have entire areas of knowledge that aren’t actually true but might be internally consistent, at least within certain scopes: conspiracy theories, belief in the supernatural, entire academic disciplines built on a religion or theology that not everyone believes, etc. Or even world building in fiction, the words on a page can be enough to convey ideas such that it “tricks” human brains into filling in the gaps so that they internally see a rich, fleshed out world that is entirely fictional and where specific details might not find strong direct support in the underlying text.
it has no concept of correctness
But statistical weight on what is more or less likely to be correct still makes a difference to objective quality of the outputs. If the model weights are trained on the reality that high quality university texts describe something and reflect some sort of underlying model of what is described using language, then can’t the model itself learn as much as a human could from those words on a page?
All models are wrong, but some can be useful. And different models have different quality in different domains. So although I don’t believe LLMs will overtake the hump of getting ahead of human knowledge, I also don’t believe that any given LLM can be evaluated on quality, and that Facebook’s LLMs are significantly behind other LLMs we see.
And that maybe a huge part of it is its internal process of preparing the model to evaluate the quality of its inputs, such that the output it produces can also score high on quality.
But it isn’t encoding knowledge, it’s encoding word correlations. That’s how it can get things wrong like saying fat32 won’t be good for a 64GB removable drive because fat32 only has a 2TB address space.
Or how it can get something wrong and when you point it out, it immediately sees how it was wrong. And I realize that that sounds human, but the way it gets there is very different. It’s predicting responses based off word correlations, not using knowledge recall to apply facts and relations known about the topics and generate responses from that.
ChatGPT 5.6: (Is fat32 a good option for a 64gb external drive)
FAT32 is suitable for a 64 GB external drive only when maximum compatibility is the priority.
The main limitation is that individual files cannot exceed 4 GB. That makes FAT32 unsuitable for large videos, disk images, backups, or many game files.
Better choices:
exFAT: Best general-purpose option for Windows, macOS, Linux, TVs, consoles, and other modern devices. Supports files larger than 4 GB.
NTFS: Better for a Windows-focused drive, permissions, and reliability, but has weaker write support on some non-Windows devices.
ext4: Best for Linux-only use, but Windows and macOS do not support it natively.
FAT32: Use mainly for older hardware, firmware updates, boot media, or devices that specifically require FAT32.
For a normal 64 GB external drive, I would format it as exFAT unless the device you plan to connect it to explicitly requires FAT32.
Local hardware Gemma-4-12b: (Is fat32 a good option for a 64gb external drive)
For a 64GB external drive, ExFAT is usually a better choice than FAT32.
Here is why:
The 4GB File Limit
The biggest issue with FAT32 is that a single file cannot exceed 4GB. While a 64GB drive can easily hold many thousands of small documents and photos, modern media files (high-definition videos, disk images, or large installer files) often exceed that limit. If you try to copy a 5GB file onto a FAT32 formatted drive, the copy will fail even though the drive is mostly empty.
The Solution: ExFAT
ExFAT was designed specifically for flash memory (thumb drives, SD cards, external drives). It keeps the high compatibility that makes FAT32 popular — it still works on Windows, macOS, Linux, Android, and PlayStation — but removes the file size ceiling, allowing files of virtually any size.
Summary Recommendation
Use ExFAT if you might store large video files, large installers, or want the most modern standard for a drive of this size.
Use FAT32 only if you require the highest possible compatibility with very old hardware (e.g. a DSLR camera from 15 years ago or a legacy Windows XP machine) and your files will always stay under 4GB.
Has it been shown that the human brain doesn’t model the world in a similar way, though? A huge portion of human knowledge is both stored and transmitted in the form of language. Lots of human knowledge also follows the garbage in, garbage out theory, where you can have entire areas of knowledge that aren’t actually true but might be internally consistent, at least within certain scopes: conspiracy theories, belief in the supernatural, entire academic disciplines built on a religion or theology that not everyone believes, etc. Or even world building in fiction, the words on a page can be enough to convey ideas such that it “tricks” human brains into filling in the gaps so that they internally see a rich, fleshed out world that is entirely fictional and where specific details might not find strong direct support in the underlying text.
But statistical weight on what is more or less likely to be correct still makes a difference to objective quality of the outputs. If the model weights are trained on the reality that high quality university texts describe something and reflect some sort of underlying model of what is described using language, then can’t the model itself learn as much as a human could from those words on a page?
All models are wrong, but some can be useful. And different models have different quality in different domains. So although I don’t believe LLMs will overtake the hump of getting ahead of human knowledge, I also don’t believe that any given LLM can be evaluated on quality, and that Facebook’s LLMs are significantly behind other LLMs we see.
And that maybe a huge part of it is its internal process of preparing the model to evaluate the quality of its inputs, such that the output it produces can also score high on quality.
But it isn’t encoding knowledge, it’s encoding word correlations. That’s how it can get things wrong like saying fat32 won’t be good for a 64GB removable drive because fat32 only has a 2TB address space.
Or how it can get something wrong and when you point it out, it immediately sees how it was wrong. And I realize that that sounds human, but the way it gets there is very different. It’s predicting responses based off word correlations, not using knowledge recall to apply facts and relations known about the topics and generate responses from that.
ChatGPT 5.6: (Is fat32 a good option for a 64gb external drive) FAT32 is suitable for a 64 GB external drive only when maximum compatibility is the priority.
The main limitation is that individual files cannot exceed 4 GB. That makes FAT32 unsuitable for large videos, disk images, backups, or many game files.
Better choices:
exFAT: Best general-purpose option for Windows, macOS, Linux, TVs, consoles, and other modern devices. Supports files larger than 4 GB.
NTFS: Better for a Windows-focused drive, permissions, and reliability, but has weaker write support on some non-Windows devices.
ext4: Best for Linux-only use, but Windows and macOS do not support it natively.
FAT32: Use mainly for older hardware, firmware updates, boot media, or devices that specifically require FAT32.
For a normal 64 GB external drive, I would format it as exFAT unless the device you plan to connect it to explicitly requires FAT32.
Local hardware Gemma-4-12b: (Is fat32 a good option for a 64gb external drive) For a 64GB external drive, ExFAT is usually a better choice than FAT32.
Here is why:
The 4GB File Limit
The biggest issue with FAT32 is that a single file cannot exceed 4GB. While a 64GB drive can easily hold many thousands of small documents and photos, modern media files (high-definition videos, disk images, or large installer files) often exceed that limit. If you try to copy a 5GB file onto a FAT32 formatted drive, the copy will fail even though the drive is mostly empty.
The Solution: ExFAT
ExFAT was designed specifically for flash memory (thumb drives, SD cards, external drives). It keeps the high compatibility that makes FAT32 popular — it still works on Windows, macOS, Linux, Android, and PlayStation — but removes the file size ceiling, allowing files of virtually any size.
Summary Recommendation