Hacker News Reader

I think to some extent it's possible to reduce cognitive load even on these simpler actions just because you have to see less unrelated data on what you asked about. I say this as someone who doesn't really use LLM integrations.

And these type of requests consume very little tokens in comparison to almost any programming work.

View on HN

But asking yourself "can I trust this information?" is the baseline amount of cognitive load added to the interaction.

Depending on the level of trust or importance of the decision this may already be a fairly high bar to clear before being able to claim any overall reductions in the interactions itself.

Yes, I definitely agree. Though there's a lot more stuff that I can trust them with nowadays, that I couldn't before.

Reply on news.ycombinator.com