56,966 blogs · 4,417,066 posts Claim your blog

Record · corpus.blog/posts/01a0dcd2-3bc6-72c9-9188-c4aa5957a938

Does training LLMs with RL improve their ability to reason?

agarriga.substack.com · published 22 November 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at agarriga.substack.com Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 14
Words captured: 1,504

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://x.com/doomslide

x.com

https://x.com/AdriGarriga/status/1991601323494764573

x.com

https://x.com/doomslide/status/1991591415055581645

x.com

https://arxiv.org/pdf/2504.13837

arxiv.org

https://arxiv.org/abs/2508.15878

arxiv.org

https://www.quantamagazine.org/amateur-mathematicians-find-fifth-busy-beaver-turing-machine-20240702/

quantamagazine.org

https://gwern.net/scaling-hypothesis

gwern.net

https://substackcdn.com/image/fetch/$s_!KIkY!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1e6d906b-0497-460a-8622-fdcdad18241b_1200x800.jpeg

substackcdn.com

Make your Statistics Sound with this One Cheap Trick Read at the source ↗

agarriga.substack.com

Policy gradients (part 1): what is it? Read at the source ↗

agarriga.substack.com

https://en.wikipedia.org/wiki/Infinite_monkey_theorem

en.wikipedia.org

https://substackcdn.com/image/fetch/$s_!xHjk!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0c8eb303-35f8-41bd-8c73-82823e90538c_1650x1454.png

substackcdn.com

https://substackcdn.com/image/fetch/$s_!1DPX!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd9a6c59b-4ca9-4de4-ae4e-87686dbbe9dc_1656x838.png

substackcdn.com

https://x.com/leopoldasch/status/1799126227724410908

x.com