Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

github.com

Post reply on HN
Print view View original

11–20 of 201 posts

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#11

Post by dylan604 »

Aurornis wrote: post #7
tbrownaw wrote: post #5

Sure it uses a few GB just like everything else these days, but some of the comments also mention it being slow?

The GitHub issue is AI generated. In my experience triaging these in other projects, you can’t really trust anything in them without verifying. The users will make claims and then the AI will embellish to make them sound more important and accurate.

> AI will embellish to make them sound more important and accurate.

Did you mean than accurate rather than and accurate? Having a more accurate issue description only sounds like a good thing to me

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#12

Post by chuckadams »

MarleTangible wrote: post #4

It's incredible how many applications abuse disk access. In a similar fashion, Apple Podcasts app decided to download 120GB of podcasts for random reason and never deleted them. It even showed up as "System Data" and made me look for external drive solutions.

Someone actually still uses the built-in podcasts app?

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#13

Post by Angostura »

chuckadams wrote: post #12
MarleTangible wrote: post #4

It's incredible how many applications abuse disk access. In a similar fashion, Apple Podcasts app decided to download 120GB of podcasts for random reason and never deleted them. It even showed up as "System Data" and made me look for external drive solutions.

Someone actually still uses the built-in podcasts app?

It's absolutely fine, from what I can tell

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#14

Post by torben-friis »

MarleTangible wrote: post #4

It's incredible how many applications abuse disk access. In a similar fashion, Apple Podcasts app decided to download 120GB of podcasts for random reason and never deleted them. It even showed up as "System Data" and made me look for external drive solutions.

The system data issue on macOS is awful.

I use my MacBook for a mix of dev work and music production and between docker, music libraries, update caches and the like it’s not weird for me to have to go for a fresh install once every year or two.

Once that gets filled up, it’s pretty much impossible to understand where the giant block of memory is.

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#15

Post by Filligree »

dylan604 wrote: post #11
Aurornis wrote: post #7

Earlier quoted context omitted.

The GitHub issue is AI generated. In my experience triaging these in other projects, you can’t really trust anything in them without verifying. The users will make claims and then the AI will embellish to make them sound more important and accurate.

> AI will embellish to make them sound more important and accurate. Did you mean than accurate rather than and accurate? Having a more accurate issue description only sounds like a good thing to me

To make them sound more accurate.

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#17

Post by seanhunter »

dylan604 wrote: post #11
Aurornis wrote: post #7

Earlier quoted context omitted.

The GitHub issue is AI generated. In my experience triaging these in other projects, you can’t really trust anything in them without verifying. The users will make claims and then the AI will embellish to make them sound more important and accurate.

> AI will embellish to make them sound more important and accurate. Did you mean than accurate rather than and accurate? Having a more accurate issue description only sounds like a good thing to me

I read that as "make them sound more important and accurate than they actually are".

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#18

Post by mister_mort »

chuckadams wrote: post #12
MarleTangible wrote: post #4

It's incredible how many applications abuse disk access. In a similar fashion, Apple Podcasts app decided to download 120GB of podcasts for random reason and never deleted them. It even showed up as "System Data" and made me look for external drive solutions.

Someone actually still uses the built-in podcasts app?

AFAIK the native Podcast app for iPhone is the only way to make PC-phone podcast file syncing work. This stops you downloading the same podcast file twice, once on your PC and once on your phone.

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#19

Post by monsieurbanana »

dylan604 wrote: post #11
Aurornis wrote: post #7

Earlier quoted context omitted.

The GitHub issue is AI generated. In my experience triaging these in other projects, you can’t really trust anything in them without verifying. The users will make claims and then the AI will embellish to make them sound more important and accurate.

> AI will embellish to make them sound more important and accurate. Did you mean than accurate rather than and accurate? Having a more accurate issue description only sounds like a good thing to me

Making them look more accurate is not the same as being more accurate, and llms are pretty good at the former.

Imagine a user had a vague idea or something that is broken, then the LLM will choose to interpret his comment for what it thinks is the most likely actual underneath problem, without actually checking anything.

Re: Anthropic Cowork feature creates 10GB VM bundle on macOS without warning

#20

Post by torben-friis »

dylan604 wrote: post #11
Aurornis wrote: post #7

Earlier quoted context omitted.

The GitHub issue is AI generated. In my experience triaging these in other projects, you can’t really trust anything in them without verifying. The users will make claims and then the AI will embellish to make them sound more important and accurate.

> AI will embellish to make them sound more important and accurate. Did you mean than accurate rather than and accurate? Having a more accurate issue description only sounds like a good thing to me

“Seem important and accurate” is correct. It doesn’t imply actual accuracy, the llm will just use figures that resemble an actual calculation, hiding they are wild guesses.

I’ve run into the issue trying to use Claude to instrument and analyze some code for performance. It would make claims like “around 500mb ram are being used in this allocation” without evidence.

Post reply on HN