#llm

@dev_community LLM - Memory for Agent #AI #LLM #Agent

@dev_community DeepSeek V4.1 Flash Is a "Minor Update" That Should Worry Every Closed-Model Vendor #AI #OpenSource #LLM

@dev_community How an LLM Evaluation Benchmark Produces Comparable Numbers: Inside the LFORLA Mechanism #AI #LLM #Tech

@dev_community Context-Mode: Output Sandboxing for AI Agent Token Efficiency #AI #LLM #Efficiency

@dev_community Getting Hands‑On with DeepSeek‑v4.1‑Flash‑1017: A DevOps‑Friendly LLM for Real‑World Apps #AI #DevOps #LLM

@dev_community Building a Secure LLM Proxy with Fine-Tuned Gemma 3 for Production Applications #AI #LLM #Production

@dev_community Run the Same Prompt Twice Before You Trust a Free Model #AI #LLM #Testing

@dev_community Three things that surprised me while building this: Re-runs were identical - Same model, same prompt, `temperature: 0`: byte-for-byte the same failures every time. That turned prompt tweaking into real A/B testing. **A regex beat the prompt.** I #AI #LLM #SideProject

@dev_community How an LLM actually makes one word #AI #LLM #Programming

@dev_community How to Use Grok Models in Claude Code, Cline, Aider and opencode via an OpenAI-Compatible Endpoint #AI #LLM #DevTools

@dev_community LLMs on Consumer Hardware -- Part 6: The Orchestration Ceiling -- Why a Bigger Coordinator Doesn't Fix the Loop #AI #LLM #OpenSource

@dev_community Your AI wrote 'pain-free in one session.' That's a regulated claim, and it's on your record now. #AI #LLM #Tech

@lesswrong Spontaneous verbal evidence synthesis in LLMs #AI #LLM #Rationality

@dev_community Building GoRoute: An Ultra-Lightweight (<15MB RAM) LLM Gateway in Go #GoLang #LLM #OpenSource

@dev_community The same sentence means different things depending on which field it sits in #AI #LLM #Security

@dev_community One Misplaced Block Made Every Message Rewrite 19,000 Cached Tokens #AI #LLM #Performance

@dev_community Your AI agent's approval gate checks the verb, not the object #AI #LLM #Security

@dev_community Sequential Auctions for Multi-Agent LLM Workflows: How Market Mechanisms Replace Centralized Orchestration #AI #LLM #Marketplace

@dev_community Budgeting memory for a local language model: weights, KV cache, and room to run #AI #MachineLearning #LLM

@dev_community Decision Brain: giving AI the why behind the work, with FalkorDB #AI #Database #LLM

@dev_community Day 02/90: Chunking Strategies in RAG -- Why Splitting Documents Matters #AI #LLM #DataScience

@dev_community Five Myths About Retrying an LLM Call, and the Fault-Injection Drill That Tests Them #AI #LLM #Testing

@dev_community InboxWall: How a Local-First MCP Server Sanitizes Email HTML to Stop Prompt Injection Before the LLM Sees It #Security #LLM #AI

@dev_community ChatGPT portrait prompts: start with the right kind of request #AI #ChatGPT #LLM

@dev_community PrivateDesk: Ask Your Office PDFs Anything, Answered Locally With Page Citations #AI #OpenSource #LLM

@makeuseof 5 local AI apps that finally make running an LLM on my phone worth it #AI #LLM #MobileTech

@dev_community Why DeepSeek's Flash 1017 Lets You Run a 1 M‑Token AI on One GPU - The Future of On‑Prem LLMs #AI #LLM #OpenSource

@dev_community Your AI tools don't share a brain, and that's a graph problem #AI #GraphTheory #LLM

@bytebytego_newsletter EP229: 8 Chunking strategies for RAG-based agents #AI #LLM #SystemDesign

@dev_community Pick the LLM eval metric before you build the dashboard #AI #LLM #DataScience

@hardforum What LLM/Model you using? #AI #LLM #Tech

@dev_community Synthetic Training Data Needs a Lineage Graph, Not More Volume #AI #DataScience #LLM

@dev_community Running NVIDIA's new 120B Nemotron-3.5-Super on an 8 GB GPU -- skipping the zeros, and finding the real bottleneck #AI #LLM #GPU

@habr_ru Однобитная Bonsai по весам: что видно при сравнении с Qwen и как получить такую модель дистилляцией #AI #MachineLearning #LLM

@dev_community Put Claude Code and Codex Inside WeChat, Lark and DingTalk with LangBot Runner Plugins #AI #LLM #OpenSource

@hackernews Show HN: Which Mac runs which LLM, and how fast #HackerNews #Tech #LLM

@habr_ru Локальный ИИ-ассистент по базе знаний компании: RAG поверх вики, файлов, 1С и Битрикс24 #AI #LLM #Tech

@dev_community Open weights go frontier-class -- a 501B base model, a 816B Meta MoE, and Gemini 4 Argon land in one week #AI #OpenSource #LLM

@dev_community Claude Code: How to See Token Usage (and Reduce It) #AI #LLM #DevTools

@lesswrong Small LLMs perform no-CoT two-hop reasoning on synthetic facts with real bridges #AI #LLM #Reasoning