LessWrong 2.0 Reader

My dialect does not have the fine distinction between "clear" and "self-evident" on which you seem to be relying; please read "clear" for "self-evident" in order to access my meaning.

Having a vague concept encompassing multiple possible definitions, which you are nonetheless extremely confident is the correct vague concept, is not that different from having a single definition in which you're confident, and not everyone shares your same vague concept or agrees that it's clearly the right one.

Is the quote here: "we're here to devour each other alive"?

Prove it.

They aren't mistakes. A story shouldn't be realistic, it should be entertaining.

During inference, for each token and each layer over it, the attention block computes some vectors, the data called the KV cache. For the current token, the contribution of an attention block in some layer to the residual stream is computed by looking at the entries in the KV cache of the same layer across all the preceding tokens. This won't contribute to the KV cache entry for the current token at the same layer, it only influences the entry at the next layer, which is how all of this can run in parallel when processing input tokens and in training. The dataflow is shallow but wide.

So I would guess it should be possible to post-train an LLM to give answers like "................... Yes" instead of "Because 7! contains both 3 and 5 as factors, which multiply to 15 Yes", and the LLM would still be able to take advantage of CoT (for more challenging questions), because it would be following a line of reasoning written down in the KV cache lines in each layer across the preceding tokens, even if in the first layer there is always the same uninformative dot token. The tokens of the question are still explicitly there and kick off the process by determining the KV cache entries over the first dot tokens of the anwer, which can then be taken into account when computing the KV cache entries over the following dot tokens (moving up a layer where the dependence on the KV cache data over the preceding dot tokens is needed), and so on.

My estimates about future value don't hinge on nanotech. I'm expecting immortal digital humans to be able to populate our lightcone without it. Why is nanotech particularly key to anything?

Plus, we're already well into the misuse danger zone... And heading deeper fast.

Religion is good and improves people's lives. Believing true things about the world has almost nothing to do with the quality of your life, or whether it is worth living.

A definition of physics that treats space and time as fundamental doesn't quite work, because there are some theories in physics such as loop quantum gravity in which space and/or time arise from something else.