"Is my Large Language Model a Strange Loop?" by Zac Hatfield-Dodds (Strange Loop 2023)

Large Language Models aren't just the new hotness - they also offer fascinating glimpses of an alternative approach to software which is evolved instead of written. We'll explore emergent representations and composition of concepts from the inside outwards; and then turn around and consider some emergent behaviors and feedback loops from the outside of the training process. Whether you're curious about superposition, induction, self-evaluation or self-correction... by the end of the talk you'll have more questions than you started with!
Zac Hatfield-Dodds
Assurance Team Lead @ Anthropic
Zac (zhd.dev) is an Australian software engineer and researcher working in San Francisco, on AI safety research by day and on property-based testing by night. He co-maintains open-source projects such as Hypothesis, Trio, and Pytest; has been elected a Fellow of the Python Software Foundation; and swears that he'll finish writing his dissertation someday. If he's not at a computer, Zac is probably some combination of camping in a national park, reading a book or three, and munching on dark chocolate.
----
Recorded Sept 21, 2023 at Strange Loop 2023 in St. Louis, MO.
thestrangeloop...

[@RobArnoldSD]

Fascinating. Really interesting and thought provoking. Way to pull it off on last minute request.

[@cmw3737]

Maybe AGI derived from LLMs is what creates/created the universe in the first place and the whole universe is a strange loop.

[@chunkyMunky329]

Must be some pretty big servers to be powering the universe! Who is paying the power bill? And if Greta convinces society to stop using electricity does it mean that the universe will disappear?