BLUE
MB
Manuel Baltieri
@manuelbaltieri.bsky.social
Chief Researcher at Araya, Tokyo. ALife, AI, embodied and enactive cognition. Information, control and applied category theory for cognitive science. manuelbaltieri.com/
120 followers74 following16 posts
Reposted by Manuel Baltieri
COcianodonnell.bsky.social

"These authors contributed equally: John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, Alex Bridgland, Clemens Meyer,...[6 more people].., Demis Hassabis" www.nature.com/articles/s41...

Highly accurate protein structure prediction with AlphaFold - Nature
Highly accurate protein structure prediction with AlphaFold - Nature

AlphaFold predicts protein structures with an accuracy competitive with experimental structures in the majority of cases using a novel deep learning architecture.

0
Reposted by Manuel Baltieri
Aamandagefter.bsky.social

A scientific paper is never finished, only abandoned.

2
Reposted by Manuel Baltieri
BRbeenwrekt.bsky.social

Lecture 24, Part 2: What did we learn from Game Theory? Game Theory, as a means of understanding humans and human economies, was a failure. But it taught us so much about games and why they captivate us.

The Only Winning Move
The Only Winning Move

Game Theory is a cautionary tale about decision making under uncertainty.

1
MBmanuelbaltieri.bsky.social

Looking at some old documents, this popped out. So refreshing! "Are theoretical results 'results'?" Abstract: "Yes." elifesciences.org/articles/40018

1
Reposted by Manuel Baltieri
CTcarlbergstrom.com

1. Imagine we land a space probe on one of Jupiters’ moons, take up a sample of material, and find it is full of organic molecules. How can we tell whether those molecules are just randomly assembled goo or the outcome of some evolutionary process taking place there? 🧪

20
Reposted by Manuel Baltieri
CBcblei.bsky.social

New blog-post by Yogi Jaeger on the "assembly theory" paper: "It maybe wasn't the best decision to call the paper "Assembly theory explains and quantifies selection and evolution" because this grandiose title raises expectations the paper utterly fails to meet." www.johannesjaeger.eu/blog/assembl...

Assembly Theory is Cool ...
Assembly Theory is Cool ...

Disclaimer: I am currently funded by the John Templeton Foundation (JTF). If you'd like to know more about my research project, you can find lots of information (and my book draft) here . I'm...

0
Reposted by Manuel Baltieri
Ppaper.bsky.social

[28/30] 94 Likes, 63 Comments, 2 Posts 2309.12288, cs․CL | cs․AI | cs․LG, 21 Sep 2023 🆕The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" Lukas Berglund, Meg Tong, Max Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, Owain Evans

We expose a surprising failure of generalization in auto-regressive large language models (LLMs).  If a model is trained on a sentence of the form "A is B", it will not automatically generalize to the reverse direction "B is A".  This is the Reversal Curse.  For instance, if a model is trained on...
1
Reposted by Manuel Baltieri
Mmanybabies.org
Reposted by Manuel Baltieri
CTcarlbergstrom.com

Most academics know that MDPI is not the most reputable publisher but this is particularly grim: a special issue in which 27th of the 28th papers are authored by the two guest editors. https://www.mdpi.com/journal/processes/special_issues/Biologics_Botanicals

15
MBmanuelbaltieri.bsky.social

What am I missing @hakwan.bsky.social ?

1
MB
Manuel Baltieri
@manuelbaltieri.bsky.social
Chief Researcher at Araya, Tokyo. ALife, AI, embodied and enactive cognition. Information, control and applied category theory for cognitive science. manuelbaltieri.com/
120 followers74 following16 posts