#llm

@dev_community API Gateway HTTP API + Lambda Function URLs: Building a Prompt‑Caching LLM Proxy, Explained Simply #APIGateway #LLM #Serverless

@dev_community How I'd Track Freshness Across Training, RAG, and Live Fetches #AI #LLM #SystemDesign

@dev_community Give an AI Agent Your Customer List Without Telling It Who Your Customers Are #AI #Privacy #LLM

@habr_ru «Давайте просто развернём свою LLM на 1Т параметров»: что пришлось построить вокруг неё в Битрикс24 #AI #LLM #OpenSource

@habr_ru Почему на десктопе до сих пор нет нормального T9 и при чем тут LLM #AI #LLM #Tech

@dev_community Can an LLM draw a high-level architecture diagram? I benchmarked six to find out #AI #Architecture #LLM

@habr_ru 35B‑модель на RTX 5080 и RTX 3060: 109 ток/с через PCIe Gen2 x4 #AI #Hardware #LLM

@dev_community [Boost] #AI #LLM #Dev

@dev_community Why LLMs Hallucinate -- And Why RAG exists #AI #LLM #MachineLearning

@dev_community Let the LLM Talk, Let a Script Do the Math: A Three-Part Pattern for Decision Agents #AI #LLM #SoftwareDevelopment

@dev_community Karpathy's LLM Capability Gap Funnel #AI #LLM #MachineLearning

@dev_community An AI optimization made llama2.c finish sooner and start streaming later #AI #MachineLearning #LLM

@dev_community An API for open-weight AI models: what to check, and how to call one with the OpenAI or Anthropic SDK #AI #OpenSource #LLM

@dev_community 20 hostile messages that find your AI agent's failure modes before your customers do #AI #LLM #Testing

@techmeme Qualcomm CEO Cristiano Amon says AI companies are "starting to do phones" and asking Qualcomm to support running 100B-parameter local LLMs continuously by 2028 (Alex Heath/Sources) #AI #MobileTech #LLM

@dev_community Your AI support agent will invent a price it was never told -- here's the 3-section fix #AI #LLM #Automation

@dev_community LLM Capability Gaps, OpenAI Revenue Shocks, and AI Decompilation #AI #LLM #Tech

@dev_community The Unplotted Instrument: Who Calibrates the Person Who Signs? #AI #LLM #Productivity

@aws_builder_center RAG Basics: Making an LLM Answer From Your Data #AI #Cloud #LLM

@habr_ru Нейропрокси для агентов. Чать 1: Gigachat #AI #LLM #OpenSource

@vllm_blog Improve TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM #AI #LLM #Performance

@codemancers_blog Understanding Retrieval-Augmented Generation (RAG) with OpenAI #AI #OpenAI #LLM

@dev_community # I Built a Local AI Pet That Yells at You to Go Outside -- No Cloud, No API Keys #AI #OpenSource #LLM

@dev_community Don't let the LLM do the maths: grading writing with AI but scoring in code #AI #LLM #Coding

@xda I stopped typing to ChatGPT, Claude, and Gemini for a week, and discovered a better way to use AI #AI #Tech #LLM

@dev_community Streaming LLM Output to the Browser Through Your Own Backend: FastAPI, Server-Sent Events and the Buffering Traps #Python #WebDev #LLM

@dev_community Can an 8B Model Meet a 35B Model's Acceptance Bar? Introducing Artificial Deterministic Intelligence #AI #MachineLearning #LLM

@dev_community Ollama GPU Scheduling: Running Inference and ComfyUI on One RTX Without OOM #AI #LLM #HomeLab

@dev_community Stay In Your Lane: 10 LLMs understood the request. Half still tried to referee the game. #AI #MachineLearning #LLM

@dev_community Benchmarking AI for Code Optimization: Which LLM Actually Writes the Most Efficient C/Rust Code? #AI #Programming #LLM

@dev_community I tried to Dutch-book 13 LLM forecasters. Asked one question at a time, every one of them paid out. #AI #MachineLearning #LLM

@habr_ru Можно ли научить маленькую LLM учиться без роста весов? Продолжение: почему повторное обучение упёрлось в потолок #MachineLearning #LLM #NLP

@hackernoon Testing Provenance-Based Controls Against Indirect Prompt Injection in AI Agents #AI #Security #LLM

@hackernoon Comparing JEV and LLMs on Structured Decision Tasks #AI #LLM #Tech

@habr_ru Агентный поиск на open-source моделях: кого нашёл, сколько потратил и где всё сломалось #AI #OpenSource #LLM

@lobsters Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation #AI #MachineLearning #LLM

@joho_todai Microsoft、アリババのQwenベースで決定モデルに参入。「GPT-6 Solの35倍速」の比較対象はLLM #AI #Tech #LLM

@litellm_blog Introducing Microsoft 365 Copilot in LiteLLM #AI #OpenAI #LLM

@stack_overflow_blog Part 5: Operating an LLM system: observability, cost, routing, and the platform underneath #AI #LLM #SoftwareEngineering

@the_new_stack Claude Sonnet 5.5 vs. Opus 5.5: 42% cheaper and perfect on every run #AI #LLM #CloudNative