AI News · #language-models

Hacker News (front) · 10일 전 제목번역

GitHub - marcelroed/gigatoken: GB/s 속도의 언어 모델 토큰화

GitHub - marcelroed/gigatoken: Language model tokenization at GB/s

Article URL: <a href="https://github.com/marcelroed/gigatoken/">https://github.com/marcelroed/gigatoken/</a> Comments URL: <a href="https://news.ycombinator.com/item?id=4…

#llm #language-models #gpu #performance #tokenization

Hacker News (front) · 2026-07-14 제목번역

Claude가 load-bearing을 반복하는 것을 멈추는 방법

How to stop Claude from saying load-bearing | jola.dev

Article URL: <a href="https://jola.dev/posts/how-to-stop-claude-from-saying-load-bearing">https://jola.dev/posts/how-to-stop-claude-from-saying-load-bearing</a> Comments …

#language-models #claude #prompt-engineering #model-behavior #ai-quirks

Hacker News (front) · 2026-07-03 제목번역

Leanstral 1.5: 모두를 위한 증명

Leanstral 1.5: Proof abundance for all

Article URL: <a href="https://mistral.ai/news/leanstral-1-5/">https://mistral.ai/news/leanstral-1-5/</a> Comments URL: <a href="https://news.ycombinator.com/item?id=48780…

#model-release #language-models #efficiency #mistral #inference

Hacker News (front) · 2026-07-03 제목번역

로컬 LLM 실행에 관한 모든 것

GitHub - jamesob/local-llm: Everything I know about running LLMs locally

Article URL: <a href="https://github.com/jamesob/local-llm">https://github.com/jamesob/local-llm</a> Comments URL: <a href="https://news.ycombinator.com/item?id=48775921"…

#open-source #language-models #llm-inference #local-llm #deployment

Hacker News (front) · 2026-06-27 제목번역

DSpark: 추측적 디코딩을 통한 LLM 추론 가속

DSpark: Speculative decoding accelerates LLM inference [pdf]

Article URL: <a href="https://github.com/deepseek-ai/DeepSpec/blob/main/DSpark_paper.pdf">https://github.com/deepseek-ai/DeepSpec/blob/main/DSpark_paper.pdf</a> Comments …

#deepseek #language-models #llm-inference #performance-optimization #speculative-decoding #inference-acceleration

Hacker News (front) · 2026-06-19 제목번역

GPT-5.5가 MIT 라이선스 GLM-5.2보다 3배 더 환각함

GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2

Article URL: <a href="https://arrowtsx.dev/bigger-models/">https://arrowtsx.dev/bigger-models/</a> Comments URL: <a href="https://news.ycombinator.com/item?id=48600167">h…

#language-models #model-comparison #gpt-5 #open-weights #hallucination #glm-5

Hacker News (front) · 2026-06-16 제목번역

GPT-NL: 네덜란드의 주권 언어 모델

GPT‑NL: a sovereign language model for the Netherlands

Article URL: <a href="https://www.tno.nl/en/digital/artificial-intelligence/gpt-nl/">https://www.tno.nl/en/digital/artificial-intelligence/gpt-nl/</a> Comments URL: <a hr…

#open-source #language-models #gpt #sovereign-ai #netherlands