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

We hacked Gemini's Python sandbox and leaked its source code (at least some)

landh.tech

Post reply on HN
Print view View original

31–40 of 151 posts

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#31

Post by topsycatt »

hnuser123456 wrote: post #26
topsycatt wrote: post #15

Earlier quoted context omitted.

That's a good question! It's not incompatible, it's just a matter of getting the flow right. I can't comment too much on that process but I'm excited for the possibilities there.

Oh, I see Gemini can run code as part of the thinking process. I suppose the sandbox that happens in was the target of this research, while code editing in Gemini Canvas just has a button to export to Colab for running. The screenshots in the research show a "run" button for generated code in the chat, but I'm not seeing that exact interface. In any case, I share your excitement.

Canvas actually has a mix of this sandbox (with a different container) and fully client-side.

The "run" option for generated code was removed due to underutilization, but the sandbox is still used for things like the data analysis workflow and running extensions amongst other things. It's really just a general purpose sandbox for running untrusted code server-side.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#32

Post by koakuma-chan »

topsycatt wrote: post #18
fragmede wrote: post #14

Earlier quoted context omitted.

Do you think "hacked Gemini and leaked its source code" is an accurate representation of what happened here?

I'm on the Google side of the equation. I think the title is a bit sensationalized, but that's the author's prerogative.

> but that's the author's prerogative

You submitted this.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#33

Post by topsycatt »

koakuma-chan wrote: post #32
topsycatt wrote: post #18

Earlier quoted context omitted.

I'm on the Google side of the equation. I think the title is a bit sensationalized, but that's the author's prerogative.

> but that's the author's prerogative You submitted this.

I submitted this HN link with a title that exactly matches the one on the article, but I didn't write the title on the article. AFAIK HN posts should match the title of the article they link to.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#34

Post by topsycatt »

devdudect wrote: post #30
topsycatt wrote: post #18

Earlier quoted context omitted.

I'm on the Google side of the equation. I think the title is a bit sensationalized, but that's the author's prerogative.

When are we going to be able to run sandboxed php code?

We could, it's just not high up on the priority list. Any particular reason you want php?

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#35

Post by wil421 »

koakuma-chan wrote: post #32
topsycatt wrote: post #18

Earlier quoted context omitted.

I'm on the Google side of the equation. I think the title is a bit sensationalized, but that's the author's prerogative.

> but that's the author's prerogative You submitted this.

Even better, OP shared something OP didn’t write but thought it was interesting.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#36

Post by 20after4 »

fpgaminer wrote: post #6

Awww, I was looking forward to seeing some of the leak ;) Oh well. Nice find and breakdown! Somewhat relatedly, it occurred to me recently just how important issues like prompt injection, etc are for LLMs. I've always brushed them off as unimportant to _me_ since I'm most interested in local LLMs. Who cares if a local LLM is weak to prompt injection or other shenanigans? It's my AI to do with as I please. If anything…

> reading the wrong thing from the wrong backalley of the internet, and suddenly they are taken over by a mind virus of sorts. What a wild future.

This already happens to people on the internet.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#37

Post by dang »

paxys wrote: post #9

Funny enough while "We hacked Google's AI" is going to get the clicks, in reality they hacked the one part of Gemini that was NOT the LLM (a sandbox environment meant to run untrusted user-provided code). And "leaked its source code" is straight up click bait.

Ok, we put the sandbox in the title above. Thanks!

(Submitted title was "We hacked Google's A.I Gemini and leaked its source code (at least some part)")

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#38

Post by marcellus23 »

koakuma-chan wrote: post #32
topsycatt wrote: post #18

Earlier quoted context omitted.

I'm on the Google side of the equation. I think the title is a bit sensationalized, but that's the author's prerogative.

> but that's the author's prerogative You submitted this.

From the HN guidelines:

> Otherwise please use the original title, unless it is misleading or linkbait; don't editorialize.

Arguably this is misleading or clickbait, but safer to err on the side of using the original title.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#39

Post by koakuma-chan »

topsycatt wrote: post #33
koakuma-chan wrote: post #32

Earlier quoted context omitted.

> but that's the author's prerogative You submitted this.

I submitted this HN link with a title that exactly matches the one on the article, but I didn't write the title on the article. AFAIK HN posts should match the title of the article they link to.

> AFAIK HN posts should match the title of the article they link to.

I am not aware of such rule's existence.

Also "should" not "must."

To be clear: I don't have a problem with you submitting this, but the title appears to be completely false.

Re: We hacked Gemini's Python sandbox and leaked its source code (at least some)

#40

Post by dang »

topsycatt wrote: post #33
koakuma-chan wrote: post #32

Earlier quoted context omitted.

> but that's the author's prerogative You submitted this.

I submitted this HN link with a title that exactly matches the one on the article, but I didn't write the title on the article. AFAIK HN posts should match the title of the article they link to.

Actually the rule is designed to let you correct misleading titles:

"Please use the original title, unless it is misleading or linkbait; don't editorialize." - https://news.ycombinator.com/newsguidelines.html

I've done that now (https://news.ycombinator.com/item?id=43509103).

I appreciate your scruples though! Because even though you would have been on the right side of HN's rules to correct a misleading (and/or linkbait) title, the fact that you work for Google would have opened you to the usual gotcha attacks about conflict of interest. This way we avoided all of that, and it's still a good submission and thread!

Post reply on HN