Hacker Newsnew | past | comments | ask | show | jobs | submit | awad's commentslogin

Amazon is generally good at 1) resolving an issue in your favor and 2) getting you to a human if needed but gosh does it feel like I've taken a different path to do so every single time I'ever needed support.

While totally unaware of the underlying economics, I do find it interesting how the major LLM providers found a way to get a non-trivial portion of consumers to actually pay for the consumer service. Of course, ads are still coming, but it was objectively impressive to go from 20+ years of "search is free" to "search is free, but capped, unless you pay us."


LLM use is not a simple search. I pay for it to either aid me or autonomously do work with document authoring, software development, and market research. It's not apples-to-apples when comparing.


if you looked at the underlying = economics - even a quick review - you'd see that paying customers is a relatively trivial portion. This is much closer to the dotcom race to maximum eyeballs; figure out the money part later.


Highly recommend adding some kind of canary like this in all LLM project instructions. I prefer my instructions to say 'always start output with an (uniquely decided by you) emoji' as it's easier to visually scan for one when reading a wall of LLM output, and use a different emoji per project because what's life without a little whim?


This stuff also becomes context poison however


Does it actually? One sentence telling the agent to call me “Chris the human serviette” plus the times it calls me that is not going to add that much to the context. What kills the context IME is verbose logs with timestamps.


Sure, but its an instruction that applies and the model will consider fairly relevant in every single token. As an extremely example imagine instructing the llm to not use the letter E or to output only in French. Not as extreme but it probably does affect.


Not only that, but the whimsical nature of the instruction will lead to a more whimsical conversation.

The chat is a simulation, and if you act silly, the model will simulate an appropriate response.


People are so concerned about preventing a bad result that they will sabotage it from a good result. Better to strive for the best it can give you and throw out the bad until it does.


La disparition[0], Georges Perec.

[0]: https://en.wikipedia.org/wiki/A_Void


Sorry, what do you mean?



Irrelevant nonsense can also poison the context. That's part of the magic formula behind AI psychosis victims... if you have some line noise mumbojumbo all the output afterward is more prone to be disordered.

I'd be wary of using any canary material that wouldn't be at home in the sort of work you're doing.


What is you tell it to end output with certain character?


It is a distraction from its intended purpose


A single emoji though?


It is not a single emoji, it's an instruction to interleave conversation with some nonsense. It can only do harm. It won't help produce a better result and is questionable at preventing a bad one.


The point is that the it _already_ treats the instructions as nonsense. The emoji is a sigil to know if it dismissing the instructions or not.


While it could stand to be more aggressive at times, especially at intersections, FSD works fairly well in NYC and can do all of less-than-legal-but-necessary things a normal driver can do (such as cross over a double yellow if there is a double parked car blocking the road) so I don't see why Waymo would have any trouble on that aspect at all.


The steak is sliced very thin and cooked (often with cheese incorporated), so think of it as more of a beef sandwich than a steak on bread.


Plenty of those memes and reels ARE focused on 'IRL' activities, though. Obviously the full experience depends on your feed, but a lot of content is created and shared around restaurants/activities/vacation etc and many millennials and Gen Z find inspiration there, whether from influencers or peers.


Are all the raised areas sitting on top of the jackscrews (where used) from 170 years ago? That itself is astounding.


No the Jackscrews would have been removed for reuse after the lift.

By the way you can still buy jacks like these. They're considered safer than hydraulic jacks and are often called "house jacks":

https://www.homedepot.com/p/Jet-20-Ton-Screw-Jack-441320/306...


No, as the article states they raised the buildings then built a new foundation underneath.


Fun fact: AMEX has been involved in international payments in one way or another for more than a 100 years and the AMEX card was the first international charge card, launched the same year as the original BofA Visa Card.


FWIW Monday night games are available on standard ESPN and, sometimes, ABC and Sunday night games are on NBC. So you don't strictly speaking need Peacock or ESPN+


But this Christmas Day you will also need Netflix if you want to watch the Texans game with Beyonce half time show. Not usre about the other Christmas Day game.


I have ESPN+ and could not watch Monday's game, it was only on ESPN and I didn't have a cable subscription.


Did not expect to see this here, but spot on.


Apparently, there are even scholarly studies on this !

Friendship and Fraternity: The Cultural Nostalgia of Adda in Modern Bengal by Nabamita Das - https://internationalconference.net/program/detail/215


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: