Comment by nerdponx | Hacker News Reader

Comment by nerdponx | Hacker News Reader

Parent Full thread

It certainly looks AI generated. Huge amount of academic "boilerplate" and not much content besides. It's broken up into chapters like a thesis but the actual novel content of each is about a page of material at most.

The Ghost UI is a nice idea and the control feedback mechanism is probably worth exploring.

But those are more "good ideas" rather than complete finished pieces of research. Do we even have an agreed-upon standard technique to quantify discrepancy between a prompt and an output? That might be a much more meaningful contribution than just saying that you could hypothetically use one, if it existed. Also how do you actually propose that the "modulation" be applied to the model output? It's so full of conceptual gaps.

This looks like an AI-assisted attempt to dress up some interesting ideas as novel discoveries and to present them as a complete solution, rather than as a starting point for a serious research program.

I appreciate the rigorous critique. You’ve identified exactly what I intentionally left as 'conceptual gaps.'

Regarding the 'boilerplate' vs. 'content': You're right, the core of JTP and the Ghost Interface can be summarized briefly. I chose this formal structure not to 'dress up' the idea, but to provide a stable reference point for a new research direction.

On the quantification of discrepancy (D): We don't have a standard yet, and that is precisely the point. Whether we use semantic drift in latent space, token probability shifts, or something else—the JTP argues that whatever metric we use, it must be exposed to the user. My paper is a normative framework, not a benchmark study.

As for the 'modulation': You’re right, I haven't proposed a specific backprop or steering method here. This is a provocation, not a guide. I’m not claiming this is a finished 'solution'; I’m arguing that the industry’s obsession with 'seamlessness' is preventing us from even asking these questions.

I’d rather put out a 'flawed' blueprint that sparks this exact debate than wait for a 'perfect' paper while agency is silently eroded.

Reply on news.ycombinator.com