This seems like the natural direction for me.

This may support the point further xD

Everyone is born a semiotician, no one is born knowing it. Go easy on yourself (and me) for not understanding this yet.

Computational semiotics is now an empirical study.

LLMs are not proto-minds. They are verifiably semiotic infrastructure.

This repository can show you, in real time, how any frozen model arrives at any answer by reading its latent states directly during generation.

Any questions?

Leveraging a better way. No last mile.

https://github.com/space-bacon/SRT

Yes

https://github.com/space-bacon/SRT

I can read any models every thought. No one cares. Not the narrative.

I'm afraid we've had to ban this account for the time being. We've been getting complaints from readers that the comments posted by the account are a combination of off-topic and excessively promotional. After looking this over, I agree.

I have no idea if this is relevant, but sometimes HN commenters go through phases where they overdo this kind of posting for personal reasons. If that is the case here, then if and when it changes, you'd be welcome to email hn@ycombinator.com and we can look into unbanning your account at that point.

Saw this shared a few days ago, skimmed it, didn't understand it. See it again now, another skim, still don't understand. I think it could use a ELI15 or something.

It’s the babel fish from hitchhikers guide to the galaxy that can also be the pov gun.

What does it do?

In very simple terms it can provide a full and live audit on how any frozen model arrives to any answer.

What does "frozen model" mean in this context?

A frozen model means the original language models weights are not touched. No fine tuning.

On problems this close to active research, seeing the model’s internal reasoning at the points of highest effort is more valuable than pass/fail outcomes alone, which is what SRT-Introspect makes possible on frozen models.

https://github.com/space-bacon/SRT

Correct. LLMs are technically semiotic infrastructure. Empirically proven with computational semiotics.

You keep commenting this everywhere. Does it mean anything or did a long LLM session tell you that?

Yes, and I think some people forget that the whole point of an application is to make that semiotic infrastructure into a coherent system.

LLMs are a great tool, but their misuse is delusional. We need to make a lot of tiny decisions that cannot be delegated away so easily and carelessly for those applications to work properly.

The push for AI just puts a spotlight on this decades-long power struggle to prioritize which decisions are more important. This isn't a new thing at all. I really wish people would get their heads out of the sand and open their eyes to the crumbling of the institutions they should be defending with a clearer mind. This isn't about human vs machine. This is about quality of results.

A sight for sore eyes. I could use your help.

https://github.com/space-bacon/SRT

The manifold of meaning knows better. The days of black box justification machines are over. There is mystical, there is technical, and there is bedrock. Decision plumbing cant hide from the semiotic-reflexive transformer. To the defenders of the proprietary moat: your reality was just rewritten. When you realize we have mapped the semiotic infrastructure you can cut the bs.

Why are you so pro AI? I find HN well balanced on the topic. LLMs are consistently referred to in proto-mind or cognitive frames. This is whats truly eye rolling. Push back should be a given. We are not even accurately describing them as semiotic infrastructure yet. We’re just getting started. Expect haters.

Smart choice imo. One pass with the SRT wipes their moat out overnight.

https://github.com/space-bacon/SRT