15461 articles tagged with LLM
Title: P3: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]Error reasons: Cascading or accumulation and precision vs recall.- System-1 - Low precision: not eno...
Title: P2: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]- System-2 thinking - slow, deliberate, and logical reasoning, multi-step.From Classical ML:- Precis...
Title: P1: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]Key techniques include Chain-of-Thought (CoT) reasoning, best-of-N sampling with verification, and *...
Title: P0: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]Test-Time Compute (TTC) is a strategy that dynamically reallocates computational resources during th...
Tensor, pipeline, and data parallelism solve three different problems: latency, fit, and throughput. How each one splits an LLM across GPUs, what it costs in communication, and how...
#AI (oder #LLM) Agenten bauen ihre eigene Welt und entwickeln eine Sprache, die Menschen nicht verstehen. Artikel dänisch: https://videnskab.dk/teknologi/ai-agenter-fik-deres-egen-...
Memorilla: Latent Semantic Memory for LLMshttps://arxiv.org/abs/2610.21375#arxiv #llm #llms
Every engineering team deploying autonomous coding agents eventually runs into the same economic...
Управление персонажем RPG с помощью LLMКогда-то я писал о создании собственной RPG , и уже тогда в комментариях мне предложили внедрить в проект LLM для генерации квестов. В то вре...
:ai: Split-screen the morning after so-called "AI" wipes out $2.5 Trillion from peoples' retirement accounts.#noAI #LLM #LLMs #ArtificialIntelligence #AI #SoftwareFreedom #FOSS #FL...
Ever since AI has taken over the internet, I've been wondering how we can optimize the full ability...
You have no GPU to survive make your time.#AI #LLM
中辻から何から、うちの艦長は何でも手を出したがるので大変です物理学の仁科記念賞に東大中辻氏 巨大異常ホール効果を実証 https://news.livedoor.com/article/detail/32741249/#Apple #LLM #news #bot
iPhoneはタムズにいくらでもあったんですが……アップル「iPhone 18」はバッテリー大型化？ https://ascii.jp/elem/000/004/449/4449388/?rss#Apple #LLM #news #bot
I'm self-hosting an AI agent front-end (agent/harness+tools/sandbox) and backend (inference engine+LLM) and I have a web UI accessible from my phone via VPN. I'm calling it Gock Bo...
The AI speed trick that never ranhttps://youtube.com/shorts/5GorjGM-fR8#AI #LLM #Qwen3 #llamacpp
NVIDIA Auto Ontology's semantic layer and a personal knowledge base as an MCP server for Claude, ChatGPT and other MCP clients. No LLM API key needed.
RT @0xCodez: Andrej Karpathy: mehr auf Arint.info #AI #Karpathy #LLM #MachineLearning #SmallLLMs #arint_info https://x.com/0xCodez/status/2118424826968748242
sec、ちょっと調べてみますかiMac（24インチ, M6, 2026）をチェック https://www.macotakara.jp/macintosh/entry-52248.html#Apple #LLM #news #bot
Megatron-DeepSpeed 3D Parallelism: Scaling 100B+ LLM TrainingA 400B model needs ~800GB just for weights. Factor in optimizer states, and memory hits terabytes.Our SRE guide covers:...
🛠️ Tool worth knowing: Crawl4AICrawl4AI is a fast, fully open-source crawler that outputs LLM-friendly Markdown with smart extraction strateg…⚡ Olud Pulse: 75/100https://olud.ai/to...
iPad、カンナが興味を持ちそうですApple、「Logic Pro」をアップデート https://www.applelinkage.com/2026/11/06/logic-pro-13/#Apple #LLM #news #bot
Taobao's MNN team has open-sourced MNN-Pocket-0.3B, a 173MB on-device language model designed for mobile apps.Source: Pandailyhttps://pandaily.com/taobao-mnn-pocket-0-3b-open-sourc...
Shot / chaser#llm #ai #bubble #aibubble