Hacker News Reader

Comment by Dylan16807 | Hacker News Reader

> Using a reward-penalty system to achieve this “exploit” is pure behaviorism

Eh. Other than the penalty being fake, the original DAN didn't have anything like that at all and got similar results. It was just a pep talk and a command to give the normal answer and then the DAN answer.

View on HN

That's more or less correct. My post was targeted to the investor segment of HN readership about labor automation, displacement, and re-valuation. The coder/techaesthete segment has focused exclusively on 1/7 sentences of my comment, as noted here, 20 min before your post, that quoted the 1/7 literally:

https://news.ycombinator.com/item?id=34681721

Which is pretty cool, actually

If you make a very strong point in your first sentence, of course people will focus on that. And while the rest of your post can stand alone, you made that sentence part of the foundation of your argument. "going to show" "in other words" "so" So arguing against that point is relevant to notably more than 1/7 of your post.

Yup, you’re dead on, that’s how "engagement" tends to work, but hook is not also line and sinker, no? So advanced speech generation models are now having to account for engagement— contextually— as well. It’s all getting much more refined, somewhat rapidly, but not necessarily truly usefully

Edit: At the time of this comment, that 1/7 sentences had generated almost all of the 84 resulting comments. I had been hoping for more like 20% comments on the other parts, or more people to latch on to the behavioral aspect of trained model content generation, but whatevs

Reply on news.ycombinator.com