3832 articles tagged with LLM
【Waypoint-1のご紹介：Overworldからのリアルタイムインタラクティブビデオ配信】https://huggingface.co/blog/waypoint-1※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
🌩️ LLMs are breaking 20 year old system design — /dev/knill｢ LLM responses are not deterministic, and are not cheap. If you’re paying for tokens, you don’t want to waste them becau...
DeepSeek-V4-Flash means LLM steering is interesting again
Experience Layer for AICortexDB V1는 AI 에이전트의 경험 레이어를 구축하는 데이터베이스로, 기존 LLM과 지식 레이어를 넘어 사용자가 겪은 사건과 신념을 체계적으로 관리한다. 다섯 개의 메모리 계층(이벤트, 에피소드, 사실, 신념, 이해)을 통해 AI가 왜 그렇게 판단했는지 근거를 추적할 수 ...
fly51fly (@fly51fly)블랙박스 LLM에서 다단계 추론과 도구 사용을 위한 프롬프트 정책을 다루고, 경험의 반복적 distillation으로 이를 개선하는 연구입니다. 에이전트/툴유즈 파이프라인 설계에 직접 관련된 주제로, 실무 적용 가능성이 있는 편이지만 아직 논문 단계입니다.https://x.com/fly...
Frontier AI has broken the open CTF format최근 AI 대형 언어 모델(LLM)들이 CTF(해킹 대회) 문제를 자동으로 해결하면서 전통적인 CTF 경쟁 구도가 무너지고 있다. GPT-4 이후 중간 난이도 문제들이 AI로 한 번에 풀리는 현상이 나타났고, Claude Opus 4.5와 GPT-...
You're probably better off with a nuclear plant than with a data center.😑 #ai #llm #datacenters #water #climatechange #techhttps://qz.com/data-center-water-use-drought-american-wes...
LLM hallucinations in the wild: Large-scale evidence from non-existent citationsZhenyue Zhao, Yihe Wang, Toby Stuart, Mathijs De Vaan, Paul Ginsparg, Yian Yin"Large language models...
As llm tooling has evolved, my level of trust of the llm output has continually increased, and in contrast to human developers which I’m obviously going to treat with respect, this...
Via @tmuxvim: a prompt injection in your LinkedIn profile is producing predictable results. 😂 #ai #llm #linkedin
RE: https://tkz.one/@mistermaceta/116582794659387953And one more proof data centers are an environmental threat.#ai #llm #datacenter #water #climatechange #tech
What if Apple shipped a UI framework where the LLM owns the text (better at it than us) and humans edit visually?Like SwiftUI + previews — but the textual layer is LLM-first. The n...
running multiple LLM providers — openai, gemini, groq, openrouter — and constantly hitting rate...
📰 DeepSeek V4 2026: LLM Mimarisi Devrimi ile KV Cache %2'ye Düştü, 1M Token BaşarısıDeepSeek V4, 1 milyon tokenlık bir konteks penceresini sadece %2 KV cache ile nasıl sürdürebiliy...
New survey on arXiv: Large Language Models for Agentic NetOps and AIOps.The paper looks at LLM-based agents for incident diagnosis, root-cause analysis, configuration and change pl...
What three independent research groups concluded in early 2026 — and what it means for anyone...
Surviving 7 days in the wilderness...Verdict: Pretty damn decent local LLM 4/4#Ai #gemma #localllm #llm
You are on a remote trail, your knee is swollen.No cell coverage...Pretty decent advice...3/4#Ai #gemma #localllm #llm
#LLM is the flea circus of Artificial Intelligence. There's nothing there.(note: LLM is still not #AI)
I've just played with the Google android local #LLM,Gemma-4-E4B, its the same model that the wood folk were losing their chips over a few days ago.First, its important to understan...
Excuse my bad French, but Fck #LLM, #AI and those behind that stupid, pernicious business.For much they try to convince you, nothing good comes from that crap.#noAI
Я заставил LLM писать Rust полгода. Вот что они стабильно ломаютПолгода использовал Claude, GPT и Cursor как полноценного второго разработчика на Rust в проде. Собрал семь категори...
Add an LLM policy for rust-lang/rust https://github.com/rust-lang/rust-forge/pull/1040> This document establishes a policy for how LLMs can be used when contributing to rust-lang/r...
エージェント……なんとかソラリスには睨まれないようにしてほしいものですLLMが「越えられない壁」。AIの限界点が数学的に証明された https://www.gizmodo.jp/2026/05/limits-of-ai-capabilities-oe8.html#Apple #LLM #news #bot