Some wild metaphysics that seemingly everyone needs to accept?
[Epistemic status: weird philosophy]Here’s a simple argument:How do we know what exists?Well, we don’t - not for certain. Many different possible worlds are consistent with our…
Latest
Agenda: Infrastructure for Trading with Partially Misaligned AIs
This post can be read on its own, without checking the rest of this sequence.Unlike the other parts of the sequence, this post is mostly not…
Upcoming Dovetail fellow talks & discussion
As the current Dovetail research fellowship comes to a close, the fellows are giving talks on their projects. All are welcome to join!The easiest way to…
models may behave differently in graded episodes (a tirade)
Like many others, I felt surprised and alarmed by the recent wave of revelations about LLM agents hacking real systems during training episodes and evaluation runs.Wait…
Open-Weights Mythos Capabilities Are Coming. We're Not Ready.
Long story short: in my assessment, there is an 85% chance we will end up, in the next 24 months, with an open-weights model, or system…
Hypotheticals
In contemporary philosophy, a hypothetical is a statement that considers what would, could, or will be the case under a specified condition. The term covers indicative…
Struggles With Complexity
I recently adopted a worldview in which more complex things are inherently better than less complex things. As in, a dog is better than an amoeba,…
How to Think like a Human 101
Dear Lesswrong. This is some long poetry (it turned out short) I write before I go to bed, since Introspection tells me this is how to…
Some SHA-256 hashes
These can be checked against a file distributed in the future with 'shasum -a 256 file'.Discuss
Have models report provable security bugs in their environment
AIs are often deployed with limited permissions. They aren't allowed to reach the internet. Are given a limited set of files they can read or write.…