Correct me if I’m wrong, but from my experience in this space in order for a model to exercise judgment it must force itself to operate in a strict chain of thought mode. Since all LLMs are predictive creatures, I started to care a lot more about my judgment settings, the transparency of them, and the presence of a judgment loop in either the development or functionality of an application built these days.
Not exactly sure where I’m going with this, but my work with creating penetesting tools for LLMs, the way that I use judgment is critical to the core functionality of the application. I agree with your concern and I will just say that the more time I spent concerned with chain of though where now I will make multiple versions of the same app using a different judge set a different “temperaments” and I found it to be incredibly enlightening as to the diversity of applications and approaches that it creates.
Even using BMAD or superpowers, I can make five versions of an app without judges involved and I feel like I’m just making the same app five times because the API begins to coalesce around the business problem you want to solve. The vicissitudes of prediction tools always want to take the safest bet for the greater good, but with the judge involved we can make the agent force itself to actually be hostile about what exactly we’re trying to do, which has produced interesting and fun results.
Not notepad++!
(Opens WhatsApp)
OpenClawd express my discontent across all my channels and draft an email to send to IT tomorrow morning. Also turn off the lights off and go to bed.
(Somewhere in china, all the lights go out)
There is capital “A” Active Listening, which is in a family of behavior modification techniques in which the interviewer can follow the aforementioned scripts to increase engagement…
And lowercase active listening, IMHO is genuinely being interested in the experiences of the person talking that your line of questioning disarms the subject into sharing stories that add personal, “cultural” context to their choices which could be considered taboo.
Beautifully said. I believe wholeheartedly that in real life, disagreements between two people hinge on an ability to disarm each other through charm and disposition. The less you know someone, and the more they appear to earnestly try to understand you - becoming heated and firing phasers just feels unbecoming; why would I perpetuate personal loneliness or ennui in a moment that is genuinely devoid of it?
I’ve found the best strategies are the ones you can abandon. clearly defined tactics and an appropriate application of people and resources require a quarterback with an ability to audible.
It’s possible to make no mistakes and still lose, it’s when people get offended about something they are wrong about that creates a tolerance for Pyrrhic victories.
Not exactly sure where I’m going with this, but my work with creating penetesting tools for LLMs, the way that I use judgment is critical to the core functionality of the application. I agree with your concern and I will just say that the more time I spent concerned with chain of though where now I will make multiple versions of the same app using a different judge set a different “temperaments” and I found it to be incredibly enlightening as to the diversity of applications and approaches that it creates.
reply