Earlier quoted context omitted.
Yeah, I suspect the main reason this was rejected is simply because it's not fixable. This is just how LLMs work. This LLM ingests untrusted data, so there will always be a non-zero chance that this type of prompt injection succeeds.
This makes me crazy. When I started my career in software the focus was on security, correctness, uptime (measured in nines--remember those?), and performance. Features are important, but building a crap feature is worse than building no feature at all. I don't understand how these systems are passing the bar. You would have been fired for trying to railroad something like this into production 10-15 years ago. What h…
Leaking YouTube creators' private videos
411–420 of 436 posts
Re: Leaking YouTube creators' private videos
#412Earlier quoted context omitted.
Because the author is wrong, and LLMs don't actually work that way. Prompt injection cannot be fixed . Role boundaries are a bandaid you can apply, but attackers can work around it.
You can still build a system that isn't vulnerable by limiting the API the LLM can access. A process consuming untrusted comments for summarisation shouldn't have access to account private data, it should just deliver a summary report. Another process can them scan that and remove/disable links etc.
(There are also problems with what you're suggesting, though, such as the summary report still being ripe for abuse in similar ways as the blog post describes.)
Re: Leaking YouTube creators' private videos
#413Earlier quoted context omitted.
It's interesting you bring up airliners. Whose engineers developed MCAS? Were any of them held liable? Are any in prison?
> Whose engineers developed MCAS? Were any of them held liable? Are any in prison? Given that Boeing had been granted wide leeway to audit itself and write its own standards... the engineers couldn't be held liable and the corrupt US government dropped the corporate case [1]. [1] https://www.bbc.com/news/articles/c891k875x3qo
Re: Leaking YouTube creators' private videos
#414Earlier quoted context omitted.
> but it’s free to use This is false. Nothing is free. We watch ads. We are tracked like animals. That time, attention and loss of privacy *is* payment. For this, it’s reasonable to expect a service that aspires to rise above shit-show.
Is free software free?
Re: Leaking YouTube creators' private videos
#415Earlier quoted context omitted.
This makes me crazy. When I started my career in software the focus was on security, correctness, uptime (measured in nines--remember those?), and performance. Features are important, but building a crap feature is worse than building no feature at all. I don't understand how these systems are passing the bar. You would have been fired for trying to railroad something like this into production 10-15 years ago. What h…
I suspect when those 10-digit wire transfers start arriving in your bank account, your attitude changes rapidly.
Personal finances aside, that's no way to run a business. Torching your brand, alienating your users, and pissing off your customers is a well known path to ruin. [edit] Even if it results in some temporary windfall--is the thesis that the windfall will be so big they no longer need users or customers? It eludes me completely what the companies that are building this trash now are hoping to achieve. It's especially galling that publicly traded companies are doing it. It's one thing for a startup to blow a bunch of venture capital on a speculative, half-baked product idea. Great risks sometimes yield great rewards. Usually they don't. Founders and VCs knowingly and willingly sign up for those risks. It's a totally different story for public companies.
Re: Leaking YouTube creators' private videos
#416Earlier quoted context omitted.
Glad to hear this is a universal big tech experience. The promo process is entirely antithetical to shipping good products
Shipping great products is about the details that almost nobody will notice A good promo process needs to notice the invisible Apple did it for decades
Back in Snow Leopard days you could instantly crash the kernel with a fuzzer. In fact I managed to do that accidentally by hand. NT kernel had much more systemic hardening than XNU.
Apple also treats employees capriciously and in non-standard ways. Your experience is almost entirely dependent on who your manager is. I have never heard any of big tech make so many false promises to employees. I have friends who negotiated for an immediate green card application upfront, but they later found out they were bait and switched, etc.
Re: Leaking YouTube creators' private videos
#417I recently left Google having worked on a number of projects with various YouTube teams. I think I can explain why it's being handled this way by YouTube. This is a fairly nuanced/involved issue, so the task of classifying the bug likely made it's way to one of the engineers responsible for the implementation of this feature. That engineer has already launched this project, and filed it away under their GRAD (perform…
But... many Googlers who have a tendency of repeating these things have (1) not seen how shittier things are on the outside (2) are not in management and do not know how much manager lies to them (3) have unrealistic expectations of how well any process applied to 100-200k people can work. If you see a place that has a better overall promo system, you'll almost certainly find that it is a much smaller shop and things are decided more ad-hoc at the top with higher information flow.
Specifically, for (2) the manager and their adjacent group can clearly flag the slipping under the rug behavior and ding one's promo. However, sometimes when they message it back they would lie about it to the employee and blame some other management or requirement or complexity, etc. Other times, the manager is a "people manager" moron and non-technical, and can't really evaluate (in which case it's not the process that's at fault, but useless management.)
It's also not clear that the optimal quality is achieved by spending more time "perfecting" things. At Google, people already work much less than other companies. Perhaps the answer is in fact the opposite: pushing to ship more milestones per unit of time and driving harder to then perfect it. My bet is if the promo packet was accepted without a full "launch"[1] they would have still shipped the same half-baked crap at a later point in time.
[1]: many years ago, they wanted to reduced half-baked "launches" and said we want "landings" not "launches" and wrote some documents explaining the difference and self-congratulated themselves. Net result: s/launch/landing in promo packets.
Re: Leaking YouTube creators' private videos
#418Earlier quoted context omitted.
5 years ago they had the same incentives.
But five years ago they had a stronger engineering culture. The old values were rapidly eroding, but some still held.
Re: Leaking YouTube creators' private videos
#419Earlier quoted context omitted.
An n-deep chain of monitors doesn't really have any defense that an (n-1)-deep chain of monitors has. None of them have the capacity to separate data and instructions. All you're doing is (in some ways) giving the model more rolls of the dice to catch what's going on, but the kind of dice and the needed values to roll are in the attacker's hands as much as yours.
Nah, I wanna see the data on it. Run the experiment
Re: Leaking YouTube creators' private videos
#420I recently left Google having worked on a number of projects with various YouTube teams. I think I can explain why it's being handled this way by YouTube. This is a fairly nuanced/involved issue, so the task of classifying the bug likely made it's way to one of the engineers responsible for the implementation of this feature. That engineer has already launched this project, and filed it away under their GRAD (perform…
[flagged]