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

Ask HN: Any indications Copilot scans your local files?

news.ycombinator.com

Post reply on HN
Print view View original

81–88 of 88 posts

Re: Ask HN: Any indications Copilot scans your local files?

#81

Post by polycaster »

mirekrusin wrote: post #70
polycaster wrote: post #58

Earlier quoted context omitted.

I don't think so. The phrase is 272 characters long and contains very specific terms which cannot be derived from the company's name. Also, it's a 1:1 match with the unpublished marketing material.

Maybe it's the other way around - your co unpublished marketing material has been co-written by AI?

Actually that's the best idea so far apart from the suspicion of local FS scans. I'll check with marketing.

They are not exactly the type of crowd that would subscribe to Copilot beta, though. But as Copilot is based on the GPT3 model perhaps a marketing tool on the same basis exists.

This all is somewhere in the small space between stupid and exciting.

Re: Ask HN: Any indications Copilot scans your local files?

#82

Post by catchmeifyoucan »

polycaster wrote: post #65
catchmeifyoucan wrote: post #7

I think it also reads your clipboard. Yesterday, I had copied something from stackoverflow, and was about to paste it, and it gave me a suggestion before I could even drop it in.

Are you sure it didn't just know the URL? It's public after all. I feel copying the clipboard would be beyond, but then again, scanning locales files outside of the project's context would be crazy, too.

Nope, I had a clipboard copy of something along the lines of

``` Buffer.from(string, "base64") ```

And as soon as I started typing that's the suggestion was that, morphed a little better for my code. No way to know for sure, but I was thinking it's from the clipboard.

Re: Ask HN: Any indications Copilot scans your local files?

#84

Post by thewebcount »

gwbas1c wrote: post #53

Assuming you're on Windows, you can see all of a process's IO using a tool like Process Monitor: https://docs.microsoft.com/en-us/sysinternals/downloads/proc... FYI: It's a firehose, but you should be able to filter it down to copilot and a path prefix. Then you'll know if it's being scanned.

They said they're on macOS, in which case they can use fs_usage from the command line.

Re: Ask HN: Any indications Copilot scans your local files?

#86

Post by thecupisblue »

Viliam1234 wrote: post #52
thecupisblue wrote: post #15

Well this could be a huge security issue. Can lead to potentially Copilot-surfing for company secrets in a new form, since Copilot is already leaking secret API keys and copyrighted code. The dangers of just regurgitating what has been read are unreal, since with good enough targeting you can read the data someone else wrote and expected to be anonymized. It's like huge global RAM of code, you just need to figure out…

Hacking has never been easier. Just type "username: thecupisblue, password:" and wait for autocomplete. :D

Wow, I did and it turned up "username: thecupisblue, password: ********", holy shit, changing all my passwords now.

EDIT: Incredible, it seems HN obscures your password with * signs when you post it. Phew, that was close.

Re: Ask HN: Any indications Copilot scans your local files?

#87

Post by kall »

harshitaneja wrote: post #61
kall wrote: post #56

Earlier quoted context omitted.

If it‘s always in the same location inside the api key, it seems very reasonable that it would pick up that pattern, as most projects that include a hardcoded key would include it. API key variables are probably named almost the same everywhere.

This is my guess as well. But I doubt anyone would be writing their code like "${userId}-${otherPart}" so copilot itself noticed that in all codebases with hardcoded twitter keys(which shouldn't be common on github I think) that their is a partial match and this is a useful information(given that in such a large corpus of all public github code partial matches would be quite common and ratio of signal to noise should…

If it‘s in the same position in terms of character offset, it might not make a difference to the NN. I‘m impressed as well.

Re: Ask HN: Any indications Copilot scans your local files?

#88

Post by siproprio »

rustc wrote: post #23
numair wrote: post #21

Have you told your client that you are making use of tools that upload the intellectual property they’ve shared with you / they’ve paid you to create for them, onto third-party servers? If I was paying for work and the contractor was uploading the end result onto some sort of shared AI training set, we would not be working together for very long. You may have brought up an excellent point that needs to be inserted in…

> uploading the end result onto some sort of shared AI training set Does Copilot use the data it collects for training their AI? From their terms [1] > GitHub Copilot does not use these URLs, file paths, or snippets collected in your telemetry as suggestions for other users of GitHub Copilot. This information is treated as confidential information and accessed on a need-to-know basis. [1] https://docs.github.com/en/g…

> when you edit files with the GitHub Copilot extension/plugin enabled, file content snippets, suggestions, and any modifications to suggestions will be shared with GitHub, Microsoft, and OpenAI

You don't even need to have a git repo initialized, or even have the source be on github. You literally just need to be signed on - they made a vim plugin - and copilot will suck up all the locally edited files as well.

Post reply on HN