ludwik

no profile record

comments

il y a 21 joursdiscuss

I would be very willing to pay more! The choice between “you may get a correct answer, or you may get lied to, without a clear way to distinguish between the two” and “you may get a correct answer, or a clear indication that the answer was not found” is pretty clear. One is a much more useful tool than the other. I don’t see any real incentives for companies making LLMs to keep their AI factually unreliable. (Full disclosure: I work for one, but I’m definitely not in the rooms where such decisions would be made.)

il y a 25 joursdiscuss

The article is about how people decide to share links, nie whether they share links at all.

le mois dernierdiscuss

Maybe that’s because I work with agentic AI in my day job, but this seems utterly obvious to me: no reasonable person would ever claim that LLMs are better at keeping secrets or enforcing rules than human employees.

This notice is not about comparing humans and LLMs. It seems that the system was designed in the only reasonable way: with a deterministic permissions layer separate from the agent. But that layer failed to work properly.

So the notice is comparing the difference between how the system was supposed to work and how it actually worked in reality. Normal post-mortem stuff.

le mois dernierdiscuss

> Do you mean things like system prompts or things in Claude.md?

All of it - system prompts, user prompts, few-shot examples, Claude.md, things that an agent learned by exploring its environment...

> So when I /compact my session what's that even the equivalent of I wonder.

Sleep? :)

le mois dernierdiscuss

I like to dunk on Meta as much as the next guy, but I think this makes sense: deterministic verification like this is not, and should never be, the LLM’s job. The tools it has access to should enforce the permissions layer, ensuring that the LLM can never perform actions the user themselves should not be allowed to perform. In this case, the tool failed to do that.

le mois dernierdiscuss

Is it? Both supervised learning and reinforcement learning are ways of training the model, and the difference between them is not that big. I would say that innate means "in the weights", while non-innate means things the model learned during inference, during its "lifetime".

le mois dernierdiscuss

I think this is exactly it, but let me ask another question (which is not rhetorical, I really don't know). Does the fact that one can describe what consciousness is and where it came from in humans help them to detect it in non-human and/or non-biological entities?

le mois dernierdiscuss

And also "instilled during their reinforcement training", and we are currently pushing planning hard there, for autonomous agents.

il y a 2 moisdiscuss

This was said in the context of a person predicting a stock market bust, so of course a stock market index price is the relevant number here.

il y a 2 moisdiscuss

It’s obviously not a new model capability. But using this well-known, existing capability to solve this particular issue is only obvious after the fact.

It’s a useful trick to have in one’s toolbox, and I’m grateful to the author for sharing it.

il y a 2 moisdiscuss

Performing 40 songs in exchange for a property does seem like serious effort...

il y a 3 moisdiscuss

The top comment categorized scraping as abuse ("abuse such as [...] scraping") - that's precisely why some accuse its author of lack of self awareness.

il y a 5 moisdiscuss

Perhaps LLMs have mimicked the style because authors have popularized it and clearly it serves some benefit to readers.

il y a 6 moisdiscuss

Shouldn't the code say:

    position = (position + direction + 1) % 12;

Or have I misunderstood something?

il y a 7 moisdiscuss

> Just had the sitename put into the value of the cookie since, and never really needed to think about that.

How would that help? This doesn't seem like a solution to the CSRF problem

il y a 7 moisdiscuss

As a childless OMSCS graduate, I also can’t imagine doing it while having kids, because it took basically all of my free time. That said, I met quite a few people in the program who were in situations similar to yours. I have no idea how they managed it, but they somehow did.

il y a 7 moisdiscuss

> In that case the winning strategy would be to switch hedge funds every 3 years.

When you flip a coin, you can easily get all heads for the first 2-4 flips, but over time it will average out to about 50% heads. It doesn’t follow from this that the winning strategy is to change the coin every 3 flips.

il y a 7 moisdiscuss

Okay? I specifically responded to your comment that the parent comment implied "if you make a mistake and say sorry you are also a psychopath", which clearly wasn’t the case. I don’t get what your response has to do with that.

il y a 7 moisdiscuss

I think the point of comparison (whether I agree with it or not) is someone (or something) that is unable to feel remorse saying “I’m sorry” because they recognize that’s what you’re supposed to do in that situation, regardless of their internal feelings. That doesn’t mean everyone who says “sorry” is a psychopath.

il y a 8 moisdiscuss

But this sounds like an ideal setup, doesn't it? Tim is fantastic at execution, but he does need a shot of big-picture vision every now and then. Tim as CEO with Steve as Chairman, steering the broader direction, feels like it could have been a perfect pairing. The issue with how things actually turned out is that Tim ended up on his own - all execution, no vision.