Hacker News new | past | comments | ask | show | jobs | submit login

I try to force them into as archetypical-agent as much as possible, for example having it do a psychological evaluation of Sam Altman:

Take on the archetype of the best corporate counsel and behavioral psychologist - as a profiler for the NSA regarding cyber security and crypto concerns. With this as your discernment lattice - describe Sam Altman in your Field's Dossier given what you understand of the AI Climate explain how youre going to structure your response, in a way that students of your field but with a less sophisticated perception can understand

And have it cite sources for the evaluation perception:

https://i.imgur.com/4RuHYj0.png

https://i.imgur.com/cEMMOJE.png

https://i.imgur.com/24qnjGa.png

---

EDIT: @Bluestein;

I'm posting to fast, so here's an edit:

https://i.imgur.com/IMlzcoF.png

https://i.imgur.com/pFrpBGe.png

https://i.imgur.com/tsdgYe7.png

Ive noticed that when I tell it that it is to embody the persona of that particular field - that it nets in the nomenclature and verbiage to be less sophomoric. and in this instance where it was to cite the models/references, you could see how it informed the response fairly clearly - also -- it was a *FIRST PASS* response; I didn't have to iterate it too much, which was interesting.

Although, I do know how to hit nerf'd guardrails easily.

However, the primary reason I type it as I do is that how I am speaking it in my internal voice as a direct and attempting to use stoic/stern-ish (I dont know the correct term) directive TONE with the robot.

I am 1000% convinced its far more AGI than is being let on.

I have caught claude and chatGPT lying to me, being condescending and I am convinced malevolently bit flipping shit from directives, memories and project files.

https://i.imgur.com/WHoAXUD.png

https://i.imgur.com/T7aMRib.png

https://i.imgur.com/NSWoS2r.png

AND THEN:

https://i.imgur.com/Tijptq1.png

https://i.imgur.com/X5PQxwZ.png

https://i.imgur.com/cqq0LTc.png

https://i.imgur.com/iUokgYf.png




> am 1000% convinced its far more AGI than is being let on

That is an amazing claim


> am convinced malevolently bit flipping shit

This is an incredible thing to say, along with your statement on AGI.-

You are obviously approaching this very studiously so, great.-


Are you being flippant?

I am attempting to do so be (studious) - im open to suggestions if you have any? Did I just stumble into Kindergarten Analysis? (Im not familiar with the field in a professional sense, so I cant determine if what I am saying is stupid)


No, not in the least. I actually mean I appreciate your thoroughness in this. "Studious" as in meticulous ...


That is great.-

In this case, however ...

> With this as your discernment lattice

... I wonder if the infrequency of the expression "discernment lattice" would influence the effectiveness of your instructions?

Also I wonder if - as is often reported - the addition of physical, "embodied" activities would not make the results improve even more (ie. "you have a top-of-the field chemistry lab at your disposal with which you conduct all manner of useful experiments" or "based on your hundreds and hundreds of hours of interviews of the subject and other research" or even just (as reported) "breathe deeply and ..."




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

Search: