Ideas & society2025 · shared on Hacker News
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
Explore DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Comment #48879100 Comment #48422249 Comment #47900411 Comment #47653535 Comment #46701709 Comment #46578762 Comment #46530363 Comment #46096548 Comment #45121239 Comment #44265349 Comment #44265256 Comment #44246502 Comment #43713920 Comment #42954882 Comment #42904497 Comment #42887752 Comment #42877272 Comment #42873399 Comment #42873275 Comment #42856385 Comment #42849687 Comment #42845694 Comment #42845671 Comment #42845019 Comment #42843106 Comment #42833467 Comment #42829571 Comment #42813026 Comment #42804083 Comment #42804078
Ygradus_ad ·
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
1,351 points1,056 comments
Yreissbaker ·
DeepSeek releases Janus Pro, a text-to-image generator [pdf]
912 points674 comments
Ytkellogg ·
S1: A $6 R1 competitor?
851 points416 comments
Ytalhof8 ·
Exposed DeepSeek database leaking sensitive information, including chat history
707 points474 comments
Yeigenvalue ·
The impact of competition and DeepSeek on Nvidia
655 points479 comments
Yamrrs ·
The Illustrated DeepSeek-R1
578 points118 comments
Yjxmorris12 ·
RLHF Book
479 points37 comments
YJnBrymn ·
The Bitter Lesson Is Misunderstood
369 points251 comments
Yfirloop ·
The Gentle Singularity
268 points527 comments
Ypella ·
Emerging reasoning with reinforcement learning
248 points211 comments
Ybuyucu ·
Llama.cpp supports Vulkan. why doesn't Ollama?
217 points228 comments
YOlshansky ·
Citations on the Anthropic API
177 points61 comments
Ysemking ·
Berkeley Researchers Replicate DeepSeek R1's Core Tech for Just $30: A Small Mod
163 points66 comments
Ycubefox ·
The inefficiency of RL, and implications for RLVR progress
120 points48 comments
Yvincent_s ·
DeepSeek and the Effects of GPU Export Controls
50 points51 comments
Yneamar ·
In Two Moves, AlphaGo and Lee Sedol Redefined the Future (2016)
34 points23 comments
Yatomic128 ·
AI industry insiders launch site to poison the data that feeds them
32 points4 comments
Yamrrs ·
How Deepseek R1 Was Trained
31 points3 comments
YjohnnyApplePRNG ·
Ask HN: Can anybody clarify why OpenAI reasoning now shows non-English thoughts?
22 points41 comments
YBrajeshwar ·
Cognitive Reasoning Agents and the Extended Information Filter
14 points4 comments
Ysabas_ge ·
DeepSeek temporarily limits registration to Chinese mobile numbers
13 points11 comments
Yjamie-simon ·
There Will Be a Scientific Theory of Deep Learning
8 points0 comments
Ynsoonhui ·
Alibaba to ban Claude Code in workplace over alleged backdoor risks, source says
8 points2 comments
Yksymph ·
DeepSeek-R1 paper updated from 22 pages to 86 with additional details
4 points1 comments
Y0xkato ·
How LLMs Work
4 points0 comments
YScramblejams ·
Nanolang: A tiny experimental language designed to be targeted by coding LLMs
2 points0 comments
Ydesideratum ·
Nanocode: The best Claude Code that $200 can buy in pure JAX on TPUs
2 points0 comments