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

71–80 of 151 posts

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

#71

Post by mediaman »

onemoresoop wrote: post #60
topsycatt wrote: post #16

Earlier quoted context omitted.

The google

Question: how does it feel inside google in terms of losing their lunch to OpenAi? Losing here is very loose, I don’t think OpenAI won yet but seems to have made a leap ahead of google in terms of marker share and we know google was sitting on tons of breakthroughs and research. Any panicking or internal discontent at google’s product policies? No need to answer if you’re uncomforable that your employer may hold you…

This is an unusual opinion in industry, although common with consumers.

Currently, Google has the most cost effective model (Flash 2) for tons of corporate work (OCR, classifiers, etc).

They just announced likely the most capable model currently in the market with Gemini 2.5.

Their small open source models (Gemma 3) are very good.

It is true that they've struggled to execute on product, but the actual technology is very good and getting substantial adoption in industry. Personally I've moved quite a few workloads to Google from OpenAI and Anthropic.

My main complaint is that they often release impressive models, but gimp them in experimental mode for too long, without fully releasing them (2.5 is currently in this category).

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

#72

Post by dvt »

jll29 wrote: post #55

Running the built-in "strings" command to extract a few file names from a binary is hardly hacking/cracking. Ironically, though, getting the source code of Gemini perhaps wouln't be valuable at all; but if you had found/obtained access to the corpus that the model was pre-trained with, that would have been kind of interesting (many folks have many questions about that...).

> but if you had found/obtained access to the corpus that the model was pre-trained with, that would have been kind of interesting

Definitionally, that input gets compressed into the weights. Pretty sure there's a proof somewhere that shows LLM training is basically a one-way (lossy) compression, so there's no way to go back afaik?

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

#73

Post by ryao »

topsycatt wrote: post #5

That's the system I work on! Please feel free to ask any questions. All opinions are my own and do not represent those of my employer.

I imagine you need to make and destroy sandboxed environments quite often. How fast does your code create a sandboxed environment?

Do you make the environments on demand or do you make them preemptively so that one is ready to go the moment that it is needed?

If you make them on demand, have you tested ZFS snapshots to see if it can be done even faster using zfs clone?

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

#74

Post by wunderwuzzi23 »

topsycatt wrote: post #5

That's the system I work on! Please feel free to ask any questions. All opinions are my own and do not represent those of my employer.

That's cool. I did something similar in the early days with Google Bard when data visualization was added, which I believe was when the ability to run code got introduced.

One question I always had was what the user "grte" stands for...

Btw. here the tricks I used back then to scrape the file system:

https://embracethered.com/blog/posts/2024/exploring-google-b...

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

#75

Post by snoman »

mediaman wrote: post #71
onemoresoop wrote: post #60

Earlier quoted context omitted.

Question: how does it feel inside google in terms of losing their lunch to OpenAi? Losing here is very loose, I don’t think OpenAI won yet but seems to have made a leap ahead of google in terms of marker share and we know google was sitting on tons of breakthroughs and research. Any panicking or internal discontent at google’s product policies? No need to answer if you’re uncomforable that your employer may hold you…

This is an unusual opinion in industry, although common with consumers. Currently, Google has the most cost effective model (Flash 2) for tons of corporate work (OCR, classifiers, etc). They just announced likely the most capable model currently in the market with Gemini 2.5. Their small open source models (Gemma 3) are very good. It is true that they've struggled to execute on product, but the actual technology is v…

How does Flash compare to Nova Lite? The latter looks less expensive. I haven’t really used either (used Nova Pro and it was good)

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

#76

Post by 0xbadcafebee »

topsycatt wrote: post #34
devdudect wrote: post #30

Earlier quoted context omitted.

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?

>75% of the web's server-side code is php. most of that is WordPress, but lots of people customize it, and being able to write your own themes, plugins, etc is a big deal

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

#78

Post by jemfinch »

wunderwuzzi23 wrote: post #74
topsycatt wrote: post #5

That's the system I work on! Please feel free to ask any questions. All opinions are my own and do not represent those of my employer.

That's cool. I did something similar in the early days with Google Bard when data visualization was added, which I believe was when the ability to run code got introduced. One question I always had was what the user "grte" stands for... Btw. here the tricks I used back then to scrape the file system: https://embracethered.com/blog/posts/2024/exploring-google-b...

grte is probably "google runtime environment", I would imagine.

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

#79

Post by flawn »

wunderwuzzi23 wrote: post #74
topsycatt wrote: post #5

That's the system I work on! Please feel free to ask any questions. All opinions are my own and do not represent those of my employer.

That's cool. I did something similar in the early days with Google Bard when data visualization was added, which I believe was when the ability to run code got introduced. One question I always had was what the user "grte" stands for... Btw. here the tricks I used back then to scrape the file system: https://embracethered.com/blog/posts/2024/exploring-google-b...

It says in the article - Google Runtime Environment

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

#80

Post by dataflow »

MyelinatedT wrote: post #65
onemoresoop wrote: post #60

Earlier quoted context omitted.

Question: how does it feel inside google in terms of losing their lunch to OpenAi? Losing here is very loose, I don’t think OpenAI won yet but seems to have made a leap ahead of google in terms of marker share and we know google was sitting on tons of breakthroughs and research. Any panicking or internal discontent at google’s product policies? No need to answer if you’re uncomforable that your employer may hold you…

From my perspective (talking very generally about the mood and environment here), it’s important to remember that Google is a very, very big company with many products and activities outside of AI. As far as I can see, there is a mix of frustration at the slowness of launching, optimism/excitement that there are some really awesome things cooking, and indifference from a lot of people who think AI/LLMs as a product c…

> Google is a very, very big company with many products and activities outside of AI.

Profit is what matters though, not number of products. The consumer perception is that Search rakes in the largest profits, so if they lose that, it doesn't matter what else is there. Thoughts?

Post reply on HN