I agree, but I think too if you polite or change your ongoing approach based on a LLM judgement, programmed based on your your will, you’ll need to ever check if it’s make it job properly to don’t up false flags on your emotions.
Never take LLM stuff at face value. That's why that last line in the example prompt above is important: you want to know the rationale, so that you can call bullshit. For example, the thing I joked about in that parallel comment about Grok's analysis that ~AI is an advanced LLM usage community is of course total bs. The bottom line is that nothing from an LLM can ever be valuable if it wasn't reviewed. The action lending value to LLM output is someone actually reading it and doing something with it. Like Schrödinger's cat, but for an attribute of value.
Also, you can still be a savage mf without being profiled like an enemy of the future state, I think, because that's generally what I do. Whenever I edit, I mostly just make it more direct. No one needs me to be PC, the rest of the world can take that role and hate my guts.
I understand your worry though; I hesitated to bring this up because I don't want to give people the idea that you should trust LLMs. The profile builders do though, because it's the only means they have to truly dragnet surveil - they cannot read everything I ever wrote with human eyes unless I'm directly targeted, but they can read the digest, and do the targeting based off the generated profile. [1]
Those types of implementations are threats, including corporate that wants to profile you to sell you ads or YT recommendations and then magically this profile ends up in the hands of guys that control other guys that ride around with guns to fuck you up. The only thing that changes based on who is in charge is who gets fucked up; there's always someone getting fucked. Divide and conquer.
So no, you may not always get the pure emotions on the interwebz. If you want that, let's have a rum & coke in a rum shop off the road in the middle of nowhere on some island in the Carib that isn't seeded with spooks (getting harder to find these places). I'll tell you how I really feel.
How do we think the govt is processing all these social media profiles you have to pass on a US entry form? They just feed it into GPT embeddings and the Claude integration maintained by the company we shall not name, and they already have the data. They likely already have the base profile too and just need to process some recent stuff, see if anything has changed. That's how I'd build such a system (and I used to build massive systems, tho not for surveillance, for a very long time.) Bottom line you don't want to crunch massive data just in time; you want to crunch much of it as it comes in. What you do want is check for change indicators and then re-process if something is off. ↩
Never take LLM stuff at face value. That's why that last line in the example prompt above is important: you want to know the rationale, so that you can call bullshit. For example, the thing I joked about in that parallel comment about Grok's analysis that ~AI is an advanced LLM usage community is of course total bs. The bottom line is that nothing from an LLM can ever be valuable if it wasn't reviewed. The action lending value to LLM output is someone actually reading it and doing something with it. Like Schrödinger's cat, but for an attribute of value.
Also, you can still be a savage mf without being profiled like an enemy of the future state, I think, because that's generally what I do. Whenever I edit, I mostly just make it more direct. No one needs me to be PC, the rest of the world can take that role and hate my guts.
I understand your worry though; I hesitated to bring this up because I don't want to give people the idea that you should trust LLMs. The profile builders do though, because it's the only means they have to truly dragnet surveil - they cannot read everything I ever wrote with human eyes unless I'm directly targeted, but they can read the digest, and do the targeting based off the generated profile. [1]
Those types of implementations are threats, including corporate that wants to profile you to sell you ads or YT recommendations and then magically this profile ends up in the hands of guys that control other guys that ride around with guns to fuck you up. The only thing that changes based on who is in charge is who gets fucked up; there's always someone getting fucked. Divide and conquer.
So no, you may not always get the pure emotions on the interwebz. If you want that, let's have a rum & coke in a rum shop off the road in the middle of nowhere on some island in the Carib that isn't seeded with spooks (getting harder to find these places). I'll tell you how I really feel.
How do we think the govt is processing all these social media profiles you have to pass on a US entry form? They just feed it into GPT embeddings and the Claude integration maintained by the company we shall not name, and they already have the data. They likely already have the base profile too and just need to process some recent stuff, see if anything has changed. That's how I'd build such a system (and I used to build massive systems, tho not for surveillance, for a very long time.) Bottom line you don't want to crunch massive data just in time; you want to crunch much of it as it comes in. What you do want is check for change indicators and then re-process if something is off. ↩