People are not (yet) aware what has been making everyone fat, but ozempic is making it harder to ignore that ultraprocessed foods are the culprit. So hopefully this will change.
In my experience, LLM usage follows an exponential distribution i.e. most people using LLMs are not using many resources, but a very small few are using a massive amount of resources. Most LLM usage is trivial and tiny, most of what I use LLMs for could be done by a local model with a decent web retrieval tool. What some people I know use LLMs for requires massive volumes of tokens. Its that small power user base which I would bet they are targetting.
I think this falls flat for a technical audience because we already know how to do this stuff. But there are a lot of people who don't know how to copy paste, or use reverse image search, or apply a filter to a table. Being able to use plain language to do these things is a game changer for them. Sure, it's inefficient and inelegant but it's an interface that will do for basic technical stuff what the ipad touch screen did for the mouse and keyboard.
That is the biggest threat - and likely where things will end up eventually… it’s when that “eventually” is and what the server based providers can pivot to in that time.
This will probably happen unless the industry conspires to roll back the availability of general computation so common people can only own computers with enough power to be glorified thin clients. The way this might look is good hardware never officially being banned, just priced too high for anybody to afford, and produced in small quantities to keep it that way while all production shifts to making massively expensive powerful hardware for corporate buyers.
Seems unlikely. We're already seeing specialized hardware optimized for LLM performance (taalas, groq, cerebras), and simple economies of scale result in these sorts of products being a better value when rented from a server vs purchased/managed/upgraded for the typical the user.
Frontier models will continue to be either exclusively available from servers or significantly more affordable from servers vs local alternatives for the foreseeable future.
I read/listened/sampled a lot this year but a few have reached out into my life and changed me at least a little bit.
- In Defense of Food - Michael Pollan. A brilliant "not diet" book about not eating crap and enjoying chocolate cake with your friends. I followed this up with Ultra Processed People to arm myself with the facts to defend not eating the junk people call food.
- The Dispossesed - Ursula Le Guin: recommended in previous year's HN what did you reads. An absolutely triumph for how it manages to portray a believable anarchist society.
- Adult Children of Alcoholics: useful to the multitude of us who grew up with an alcoholic parent(s). I used this to identify the common patterns I share with others who grew up like me. You are not alone!
- The Invention of Clouds (not finished): I really like the context of "dissenting science" which the author conveys brilliantly. Turns out Dark Academia and Bro Science are not new.
- The Art of Frugal Hedonism: Irreverant although it comes off a little pious. This book has helped me accept that I have enough stuff already.
Can't speak for OP but I largely spend it reading (and web). I bought a kindle recently because I found the ipad/iphone were too distracting to reliably avoid web surfing instead of a book. I view the switch to long form content as a form of information dieting in the same way as a switch to whole foods.
I think a lot of this is because people (and thus LLMs) use verbosity as a signal for effort. It's a very bad signal, especially for software, but its a very popular signal. Most writing is much longer than it needs to be, everything from SEO website recipes, consulting reports, and non-fiction books. Both the author and the readers are often fooled into thinking lots of words are good.
It's probably hard to train that out of an LLM, especially if they see how that verbosity impressess the people making the purchasing decisions.
> I think a lot of this is because people (and thus LLMs) use verbosity as a signal for effort.
It's also one of the main use-cases for non-programmer use of the models, so there are business-forces against toning it down. Ex: "Make a funny birthday letter for my sister Suzie who's turning 50."
There's also the very real trap of traditional forum comments being ranked higher in your brain's algorithm for "relevance" since you can explain it as reading alternative perspectives. There's real FOMO in reading news without having comments for me sometimes, because what if there's a perspective that I'm completely missing here?
Of course, long term I know time spent this way is mostly wasted for the value I get out of it.
It’s no different than traditional social media, except in intensity. It’s less intense, because of its text-based format as opposed to video, the clickbait-resistant culture, and the fact that while it’s very large, it’s not infinite. You can consume the top page under half an hour and there are only so many stories posted here a day.
Depending on where you are in the AuDHD spectrum, you can be as addicted to HN as a teenager with 7hrs daily Instagram usage. pg acknowledges this.
If HN was boring, it wouldn't have a "noprocrast" setting.
This forum is addicting to a lot of people. There are also clickbait titles (though less than elsewhere), heated debates, even flamewars in the comments.
I disagree. Debate, karma, religious tech wars, replies. All fun. I spent so much time here in the early days that I noticed my personality change. I'd been debating online so much for a few years that it was seeping into the real world me. I couldn't let people be 'wrong' without correcting them and, even if you're right, that's an annoying person to be around (I see the irony of this comment).
No smartphone can match the bottom tier super-zoom camera I have for bird photography. Even with the frankly microscopic sensor on the super-zoom the power of depth-of-field on an adjustable zoom lens is amazing.
reply