Junyan Xu

Results 169 comments of Junyan Xu
trafficstars

Evolution of McAllester's set-theoretic dependent type theory as language for mathematics: *Tarski and Mentalese*, Aug 30, 2013, https://machinethoughts.wordpress.com/2014/08/02/tarksi-and-mentalese/ *Implementation and Abstraction in Mathematics*, Jul 29, 2014, https://arxiv.org/abs/1407.7274v2 *Metaphor and Mathematics*,...

In order to change the stm (color) planes in patch-39, you need to modify the fourth and fifth parameters of `forward0` (`btm` and `wtm`): https://github.com/alreadydone/lz/blob/70a8aff1aedc9e2af5556abd928cc480fe358078/src/OpenCLScheduler.cpp#L338 https://github.com/alreadydone/lz/blob/70a8aff1aedc9e2af5556abd928cc480fe358078/src/Network.cpp#L815-L816 https://github.com/alreadydone/lz/blob/70a8aff1aedc9e2af5556abd928cc480fe358078/src/UCTSearch.cpp#L416 https://github.com/alreadydone/lz/blob/70a8aff1aedc9e2af5556abd928cc480fe358078/src/UCTSearch.cpp#L957 When I...

I believe it's possible to simply use a key-value store as memory and make it available to Auto-GPT as a tool, letting the model itself decide when and what to...

Actually, maybe we can make GPT models aware of the memory tool using the [system message](https://platform.openai.com/docs/guides/chat/instructing-chat-models) without the need of finetuning, since it's just a single simple tool. Something like...

Hmm, this merge didn't go well ... Shouldn't have squash-merged ... should be fine now.

Yeah, apparently links to bib entries are [not rendered currently](https://leanprover-community.github.io/mathlib4_docs/Mathlib/AlgebraicGeometry/EllipticCurve/Weierstrass.html#References) (compare [mathlib3](https://leanprover-community.github.io/mathlib_docs/algebraic_geometry/elliptic_curve/weierstrass.html#references)).

I know about Zapier but not Za*pp*ier :)

> currently there's no open source organisation with the amount of capital required to buy/rent that many GPUs to compete with openai/google/etc. Maybe you'd be interested in signing this petition:...

https://petals.ml/ > Run 100B+ language models at home, BitTorrent‑style > Run large language models like [BLOOM-176B](https://huggingface.co/bigscience/bloom) collaboratively — you load a small part of the model, then team up with...

Did you see https://agentgpt.reworkd.ai/ ? #174