#llm

@dev_community Version Your AI Feature: Prompts and Evals Before Model Config #AI #LLM #DevOps

@dev_community The 3 Agent Patterns That Keep Showing Up in Every Successful AI Product #AI #SoftwareDevelopment #LLM

@dev_community What Senior AI Engineers Actually Think About the Agent Hype (It's Complicated) #AI #LLM #Tech

@dev_community Meta's Muse Spark Open: 816B Parameters You Can Download Today (But Probably Can't Run) #AI #OpenSource #LLM

@dev_community Our skill-description test passed at 2,304 of 10,000 characters while Claude Code's listing sat at 94% of its budget #AI #LLM #Tech

@dev_community I don't like this topic, but the idea and the execution was very nice! #AI #LLM #Tech

@dev_community Mistral's Timestral Runs on a CPU. Its 'Modified MIT' License Stops at $20M a Month #AI #OpenSource #LLM

@vllm_blog Hyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly #AI #LLM #Optimization

@ash_furrows_blog LLMs Are Tools #AI #LLM #Tools

@vllm_blog Serving Reflection Beam on vLLM from Day 0 #AI #LLM #OpenSource

@dev_community Claude : tout ce qu'il sait faire, bien au-delà du chat #AI #LLM #Tech

@dev_community Security by Construction: Making Three Classes of AI Data Leaks Structurally Impossible(Loreflow) #AI #Security #LLM

@dev_community Mapping Self-Hosted LLM API Gateways: What the CISA Distillation Advisory Means for Asset Owners #AI #Security #LLM

@dev_community Why long context is expensive: the KV cache bill #AI #LLM #Programming

@dev_community Red-Teaming a Kids' AI Tutor: How a One-Word Variant Slipped Past Our Prompt-Injection Filter #AI #Security #LLM

@dev_community A 5-column CSV that stops your AI agents from silently burning money #AI #LLM #Python

@habr_ru Вызов инструмента без генерации: проверяю выбор функций и аргументов #AI #LLM #Programming

@dev_community Janas: Run LLMs Bigger Than Your RAM by Streaming from SSD #AI #LLM #OpenSource

@dev_community Draft the file your agent loads at every session start #AI #LLM #Agent

@habr_ru Как ИИ-агенты повторяют задачу: промпт, скилл, граф или код #AI #Programming #LLM

@dev_community NoteBank: How Replaying a Few Saved Snippets Restores Long-Context Recall in Linear-Attention Models #AI #MachineLearning #LLM

@dev_community Inside BitRun v0.2: How I Engineered a Terminal Cockpit for 1-Bit LLMs with Live Power Telemetry #AI #OpenSource #LLM

@dev_community My custom AI bot keeps giving bad advice because it cannot retain feedback from past calls #AI #LLM #Python

@xda I gave a local LLM read access to my files, and it finds things better than Windows Search ever has #AI #Tech #LLM

@habr_ru Не хакерская атака, а малые дети без присмотра #AI #Security #LLM

@habr_ru Тень стратега (2): Постановка цели #AI #LLM #Strategy

@james_governor_monkchips The best token is one you don't use - Spotify on LLM usage as an IO question #AI #LLM #Tech

@vincent_schmalbach Anthropic Merges 30,000 Changes a Day, and It Shows #AI #SoftwareDevelopment #LLM

@dev_community My LLM chat API's routing tiers taught me that 'auto' is a pricing decision, not a quality decision #AI #LLM #APIs

@dev_community Your chatbot resends the whole conversation on every message. Here's what that costs, measured. #AI #LLM #CostOptimization

@dev_community What broke when we ran agents on small local models #AI #LLM #OpenSource

@xda I moved my local models from Ollama to llama.cpp, and the reason I stayed has nothing to do with speed #AI #LLM #Tech

@dev_community Reflection AI Beam: Why 501B Parameters That Cost Like 23B Matter More Than the Leaderboard #AI #MachineLearning #LLM

@dev_community We ran the same LLM evaluation twice. Seven of eleven scores changed. #AI #LLM #SoftwareDevelopment

@dev_community RAG Evaluation: How to Measure Retrieval and Answer Quality #AI #LLM #Tech

@habr_ru Jev 1.14: ищем объекты, проверяем документы и находим кошку среди 96 фотографий #AI #ComputerVision #LLM

@mistral_blog Introducing Timestral #AI #LLM #OpenSource

@litellm_blog Day 0 Support: TypeSafe Jev 1.14: Adds images, box questions, and long context #AI #LLM #OpenSource

@dev_community Contextual Retrieval in 80 Lines: Anthropic's Chunk-Prefix Trick, Measured on Your Docs #AI #LLM #Python

@dev_community Meta's Muse Wonder Adds a Memory Layer to Its Agent Models #AI #LLM #SoftwareDevelopment