#llm

@dev_community LLM - Tool Calling & MCP #AI #LLM #APIs

@dev_community The Prompt Tweak That Fooled Us 5 Times, and the Code Gate That Actually Fixed It - Part 1 #AI #LLM #SoftwareDevelopment

@dev_community standup-sloth: a local LLM drafts your standup, and a citation check keeps it honest #LLM #OpenSource #GoLang

@dev_community What a language model says about a poker hand after it ends, next to what the log shows #AI #LLM #Poker

@dev_community Next-Concept Modeling (NCM): A New Approach to AI Language Generation #AI #MachineLearning #LLM

@dev_community LLM API Pricing: 375 Models Compared Across 137 Providers #AI #API #LLM

@dev_community Text-to-SQL on Oracle: two prompt rules took a light model from 35% to 64% #AI #Database #LLM

@dev_community Your AI's knowledge base had 61 pages. 24 of them described a company that no longer exists. #AI #LLM #Tech

@dev_community I taught a local LLM to be lazy on my behalf (sloth-alias) #AI #LLM #Productivity

@techmeme Inception launches Mercury 3, a diffusion-based LLM it claims is "comparable to Luna and Haiku models" but 4x to 8x faster, generating ~1,000 tokens per second (Jason Hiner/The Deep View) #AI #LLM #TechNews

@dev_community The no-tool case: the drawer my tool-call registry lacked #AI #LLM #SoftwareDevelopment

@joho_todai LLMの重みにバックドアを埋め込み、DNS経由で秘密を送信。隔離環境でも成立した供給網攻撃の実験 #CyberSecurity #AI #LLM

@dev_community LLM API Pricing: 375 Models Compared Across 137 Providers #AI #LLM #API

@dev_community A half-million-token prompt found both needles on my 3090 #AI #LLM #Tech

@dev_community All Nine of My Voice Agents Are One Giant Prompt. Here Is Where That Stops Working. #AI #LLM #PromptEngineering

@dev_community Day 04/90: Lost in the Middle -- Can RAG Find the Right Evidence and Still Get the Answer Wrong?_Evidence_ #AI #LLM #RAG

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

@dev_community The path to AI FDE #01: Anatomy of an LLM app request #AI #LLM #Python

@dev_community Why Tolan's $30M bet on planning over chat changes how we build AI companions #AI #Startup #LLM

@dev_community PromptShield AI: Zero-Leak Local Redaction & Prompt Hardening Engine for Open-Weight Models #AI #OpenSource #LLM

@dev_community LangChain vs. LangGraph: How to Choose the Right Framework #AI #LLM #Programming

@habr_ru Оценка агентных систем #AI #LLM #Tech

@dev_community DeepSeek V4.1 Flash 1017: what DeepSeek says changed, and swapping it in without breaking anyone's saved model #AI #LLM #OpenSource

@dev_community How Much Context Fits Beside a 12B on an 8 GB GPU? Gemma 4 12B's Context Cache on an RTX 3050 #AI #GPU #LLM

@dev_community Proposal Persistent Local Memory for AI Assistants #AI #LLM #Productivity

@google_cloud Who judges the judge? Three helpful ways to audit your LLM evaluators #AI #LLM #CloudComputing

@dev_community Why your AI agent's memory says it saved but didn't #AI #LLM #SoftwareDevelopment

@stack_overflow_blog Production-grade LLMs and agents: a field guide #AI #SoftwareEngineering #LLM

@dev_community Screen an agent project for agent washing #AI #SoftwareDevelopment #LLM

@dev_community Building a RAG Chunking Benchmark With Realistic Queries #AI #LLM #DataScience

@dev_community What Is an LLM, Really? #AI #LLM #Programming

@hardforum DeepSeek's Post-Training Lead Declares "Entering the Era of Democratized Wish-Driven Coding" As V4.1-Flash-1017 Model Smokes OpenAI's GPT-5.6 Sol #AI #OpenSource #LLM

@kdnuggets LangChain vs. LlamaIndex vs. Building From Scratch: Here's What I Suggest #AI #LLM #Programming

@dev_community Don't Let the LLM Decide: How I Built a Predictable AI Tutor #AI #LLM #SoftwareDevelopment

@dev_community A Voice License Must Stay Current #AI #LLM #SoftwareDevelopment

@dev_community Prompt injection is a trust-boundary bug in the retrieval pipeline #Security #AI #LLM

@dev_community vLLM Decision 3.0 地端實測 #AI #LLM #MLOps

@dev_community LLM Training Pipelines Need Rights Taint Tracking, Not Lineage #AI #LLM #OpenSource

@dev_community Why reasoning_effort behaves differently across providers #AI #LLM #Tech

@dev_community The RAG Verification Trap: Why AI Still Hallucinates in Production (And How to Fix It) #AI #LLM #Programming