-
Claude 5 세대 모델을 위한 새로운 컨텍스트 엔지니어링 규칙
The new rules of context engineering for Claude 5 generation models | Claude by Anthropic
<p>Article URL: <a href="https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models">https://claude.com/blog/the-new-rules-of-context-engineering-f…
-
MiMo-V2.5-Pro-UltraSpeed: 초당 1000토큰을 생성하는 1T 모델
MiMo-V2.5-Pro-UltraSpeed: 초당 1000토큰을 생성하는 1T 모델 | GeekNews
<ul> <li><strong>1조(1T) 파라미터 모델</strong>에서 디코딩 속도 <strong>1000 tokens/s</strong>를 처음으로 돌파한 모델</li> <li>전용 하드웨어가 아닌 <strong>commodity GPU</strong>만으로 속도를 달성했으며, 단일 표준 <strong>8-GPU …
-
Claude Opus 4.8: "적당하지만 실질적인 개선"
Claude Opus 4.8: "a modest but tangible improvement"
<p>Anthropic shipped <a href="https://www.anthropic.com/news/claude-opus-4-8">Claude Opus 4.8</a> today. My favourite thing about it is this note in the release announcement:</p> <…
-
Gemini 3.5 Flash: 더 비싸지만 구글이 모든 곳에 사용할 계획
Gemini 3.5 Flash: more expensive, but Google plan to use it for everything
<p>Today at Google I/O, Google <a href="https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/">released Gemini 3.5 Flash</a>. This one skipped the <co…
-
지난 6개월 LLM의 모든 것을 5분으로
The last six months in LLMs in five minutes
<p>I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the <a href="https://tools.simonwillison.net/annotated-presentations">latest ite…