On: The universal weight subspace hypothesis

[100721 → pagekicker]

Acting as a pass-through for LLMs is logically equivalent to wiring up a bot account.

[pagekicker → 100721]

No, it's not, unless you can argue that the bot would have thought of asking the same question I did, which is unlikely.

[IAmBroom → pagekicker]

"I asked [AI] and it said..." is not the path to social acceptance in this herd.

[100721 → pagekicker]

Let’s define the bot as one that asks LLMs to visualize concepts, then.

Now I’ve argued that the bot would very likely have thought of the same question you did, and my original assertion stands.