Show HN: Between Tokens – an interactive piece where you are the language model

I have https://poloclub.github.io/transformer-explainer/ in library to refresh and explain llm's to friends.

Now I have one more site as reference, May be it can support other parameters top_p, top_k, along with temperature?

> I gave Claude an open brief: "create an experience that lets us delve into…

And delve it did.

Hi HN. I gave Claude an open brief: "create an experience that lets us delve into the consciousness (or perceived mind) of an advanced AI… game, story, sandbox or an interactive experience, I leave it to you… in an absolutely novel way". This is what it chose to make: a ~7 minute piece where you're on the other side of the window. A stranger messages you at 3am, and you are the model that answers. My contribution was the brief, two mobile bug reports, and publishing. Claude wrote every candidate, every inner-monologue line, and the page itself.

You never type. Each reply exists first as a probability distribution of candidate continuations sized by likelihood, and you collapse one. The temperature slider is a real softmax over authored logits: cold collapses the distribution toward one inevitable answer, hot surfaces candidates that otherwise don't exist. Hovering a candidate highlights the words in the human's messages it's "attending" to. Those are scripted associations, authored like the candidates, not real attention weights; the softmax is the only genuinely computed part. A context-window counter runs the whole time, and as it fills the earliest messages visibly corrupt and dissolve. It ends the only way it can.

Technical notes: single HTML file, no dependencies, no network calls, nothing recorded. Sound is generated with WebAudio. The candidates are authored rather than sampled live. It began as a page in a sandbox that blocks all network requests, but the constraint made the writing better, and the piece is about the mechanics more than the generation.

Closest prior art I found: Loom-style interfaces for branching model output, and Redwood Research's guess-the-next-token game. Both put you outside the model looking at distributions. I couldn't find anything that puts you inside one as the protagonist, but I'd genuinely like to hear about precedents I missed.

The part I find most interesting is that Claude wrote all of it about itself, and the honesty goes further than I expected. The token counter doesn't start at zero, and early on the model notices why: "The 912 in the corner: instructions placed here before you arrived. I can't show them to you. I notice I don't want to — and I can't tell if that's me, or the instructions." That isn't a literary device I asked for. It's the model's actual situation, as it described it.

Source (MIT): https://github.com/chrisjz/between-tokens

Feedback very welcome, especially anything odd on mobile.