Hacker News Reader

Yeah. I just did a day with 4.7 and I won't be going back for a while. It is just too expensive. On top of the tokenization the thinking seems like it is eating a lot more too.

View on HN

What was your level methodology and results? Can't just post "too expensive" and not explain how you went about it.

yeah i am still not clear why there are 5 effort modes now on top of more expensive tokenization

Once you've seen a few results of an LLM given too much sway over product decisions, 5 effort modes expressed as various english adjectives is pretty much par for the course

choice is often a great dark-pattern (lack of choice is too but...). Choices generally grow cost to discover optimality in an np way. This means if the entity giving choice has more ability to compute the value prop than the entity deciding the choice you can easily create an exploitive system. Just create a bunch of choices, some actually do save money with enough thought but most don't, and you will gain:

People that think they got what they wanted, the feature is there!, so they can't complain but...

People that end up essentially randomly picking so the average value of the choices made by customers is suboptimal.

Reply on news.ycombinator.com