#llm

@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

@dev_community LLM Agent Task Decomposition for Reliable Workflows #AI #LLM #SoftwareDevelopment

@dev_community The Hidden Backdoor Risk in "Uncensored" AI Models #AI #Security #LLM

@habr_ru Slopsquatting: как мы 20 лет учили разработчиков не доверять пакетам, а потом всем скопом доверились LLM #AI #Security #LLM

@dev_community Is Gemini 4 Argon Free? #AI #LLM #Tech

@habr_ru Угроза ИИ-агентам: LLM снимают с продакшена уже через 6 месяцев. Почему и как подготовиться #AI #LLM #Cybersecurity

@dev_community You Put the Time at the Top of the Prompt and Paid Full Price Every Call #AI #LLM #Performance

@habr_ru Как я подружил llama-server с Claude Code: доработка Go-лаунчера для локальных LLM #AI #LLM #Go

@dev_community LLM-as-a-Judge Reliability: Check Your Grader Against Human Labels #AI #LLM #MachineLearning

@dev_community How to deploy and tune Qwen3.8-27B on one RTX Pro 6000 #AI #LLM #Hardware

@dev_community Telling a cheap model to "think a little" made it slower and sometimes silent #AI #LLM #Performance

@dev_community Is 'Prompt Auditing' for Claude Opus Real Engineering or Just Vibe-Driven Superstition? #AI #LLM #PromptEngineering

@dev_community LiteLLM Router -- Stop Hardcoding One Provider Into Your App #AI #LLM #Python

@dev_community What To Do When a Free LLM API Says 429 (A Field Playbook) #AI #API #LLM

@dev_community Run a 24B LLM on Your Phone: Deploy Liquid AI Today #AI #MobileDev #LLM

@dev_community Agent Memory Without Contamination #AI #LLM #SoftwareDevelopment

@dev_community FollowUp Local: a Gemma model on your laptop that tells you why the customer went quiet #AI #OpenSource #LLM

@dev_community How to Prevent AI From Repeating Its Own Mistakes #AI #MachineLearning #LLM

@habr_ru Асинхронное ротационное сжатие, или Как сделать бесшовной беседу с вашим локальным агентом #AI #LLM #Tech

@dev_community Claude Tool Use in Production: 6 Failure Modes and How I Handle Them #AI #LLM #SoftwareDevelopment

@dev_community Claude Opus 5.5 / Sonnet 5.5: 5 settings that return 400 when you only change the model name #AI #LLM #API

@dev_community Let the model explain, let the code count: a local LLM helper for Swiss administrative letters #Python #LLM #AI

@dev_community Gemma 4 on a Used 8 GB RTX 3050: 116 Tokens/s for One User, 618 for 64 #AI #LLM #Tech

@vllm_blog Day 0 support for Muse Spark Open on vLLM #AI #LLM #OpenSource

@vllm_blog Announcing Day 0 Support for NVIDIA Nemotron 3.5 Super VL on vLLM #AI #LLM #Tech

@dev_community LLM wiki vs. RAG: what each one is, and what I measured when I used a wiki as a RAG replacement (it was slower) #AI #LLM #Tech

@dev_community Training an LLM from Scratch on Inference-Only NPUs -- No GPU Required #AI #LLM #OpenSource

@dev_community What changes in your working day when your agent stops forgetting #AI #Productivity #LLM

@netflix_tech The Lifecycle of LLM-as-a-Judge: Building, Aligning, and Monitoring at scale #AI #LLM #Tech

@dev_community I tried to fire my LLM API. Open models passed one task and failed the other. #AI #OpenSource #LLM

@dev_community Researchers Hid a Mailbox in Offscreen Text. AI Agents Sent It 33 Messages #AI #LLM #Security

@dev_community Stop trusting a 99% uptime claim: the LLM API relay failures we hit, and how we test stability #DevOps #LLM #Reliability

@dev_community An 83-Page Teardown of 11 Coding Agents: Three Findings, Two Hands-On Checks, One Expired Constant #AI #Coding #LLM

@habr_ru Повышаем температуру, или почему один промпт дает разные сюжеты #AI #LLM #Tech

@techrepublic Liquid AI Releases LFM2.5-24B-A2B for Local AI Workflows #AI #LLM #EdgeComputing

@habr_ru Как писать текст для нейросети, чтобы она сослалась на сайт: в 60 ответах она чаще брала абзацы от 30 слов #AI #LLM #Content

@bytebytego_newsletter The Terminator Problem: How Teaching an LLM One Bad Habit Can Change Its Behavior #AI #MachineLearning #LLM

@dev_community I built an AI face rating app that shows its work: MediaPipe in the browser, an LLM on the server #AI #WebDev #LLM