ModelForge | Dark Hacker News

user:	ModelForge
created:	December 18, 2024
karma:	709

1.	GPT-6 Astra, looped transformers, and hidden reasoning(magazine.sebastianraschka.com) 513 points by ModelForge 2 days ago \| 161 comments
2.	Claude Watermarks Text: Token sampling, watermark detection, and removal(magazine.sebastianraschka.com) 3 points by ModelForge 18 days ago \| 0 comments
3.	18 days ago \| discuss
4.	How Claude's Text Watermarking Works [video](youtube.com) 2 points by ModelForge 23 days ago \| 0 comments
5.	How Claude's Text Watermarking Works(sebastianraschka.com) 5 points by ModelForge 25 days ago \| 0 comments
6.	Kimi K3 Architecture Overview and Notes(sebastianraschka.com) 507 points by ModelForge 45 days ago \| 111 comments
7.	Inkling: A New Open-Weight 975B Moe with a Few Surprises(sebastianraschka.com) 3 points by ModelForge 57 days ago \| 0 comments
8.	Claude Code's Real Secret Sauce Isn't the Model(sebastianraschka.com) 6 points by ModelForge 164 days ago \| 0 comments
9.	197 days ago \| discuss
10.	The State of LLMs 2025: Progress, Problems, and Predictions(magazine.sebastianraschka.com) 3 points by ModelForge 254 days ago \| 0 comments
11.	A Researcher's Field Guide to Non-Standard LLM Architectures(magazine.sebastianraschka.com) 2 points by ModelForge 311 days ago \| 0 comments
12.	Explanation of Gated DeltaNet (Qwen3-Next and Kimi Linear)(github.com) 3 points by ModelForge 312 days ago \| 0 comments
13.	The Core Components of Modern LLMs and the Models Beyond Transformers [video](youtube.com) 3 points by ModelForge 319 days ago \| 0 comments
14.	Popular Attention Alternatives: GQA, MLA, SWA(sebastianraschka.com) 4 points by ModelForge 331 days ago \| 0 comments
15.	Multi-Head Latent Attention(sebastianraschka.com) 4 points by ModelForge 333 days ago \| 0 comments
16.	Thinking Machines Lab Co-Founder Departs for Meta(wsj.com) 7 points by ModelForge 335 days ago \| 0 comments
17.	OpenAI's internal Slack messages could cost it billions in copyright suit(sherwood.news) 8 points by ModelForge 336 days ago \| 1 comment
18.	LLM Evaluation from Scratch: Multiple Choice, Verifiers, Leaderboards, LLM Judge(magazine.sebastianraschka.com) 4 points by ModelForge 341 days ago \| 0 comments
19.	Gemma 3 270M re-implemented in pure PyTorch for local tinkering(github.com) 417 points by ModelForge 1 year ago \| 57 comments
20.	GPT-OSS vs. Qwen3 and a detailed look how things evolved since GPT-2(magazine.sebastianraschka.com) 490 points by ModelForge 1 year ago \| 97 comments
21.	LLM Research Papers: The 2024 List(magazine.sebastianraschka.com) 5 points by ModelForge 1 year ago \| 0 comments