#llm

@dev_community The Exact Stack I Use to Build Production AI Agents (No Fluff) #AI #LLM #WebDev

@dev_community LLM API prices, AI funding and a no-key MCP server: TANDIU weekly data notes (Oct 13-19, 2026) #AI #LLM #Data

@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

@dev_community We tested the 20 most-installed agent skills with and without the skill. The most-installed one came out worse. #AI #LLM #Testing

@dev_community 95% recall, 80% answers: what LongMemEval retrieval scores don't tell you #AI #LLM #DataScience

@dev_community HotKV cut Claude token use by 70% in our Banking77 benchmark #AI #LLM #Performance

@dev_community Ground ChatGPT in Live Amazon Data: MCP Connectivity Check + a 3-Prompt Verification #AI #Data #LLM

@dev_community Do not let the agent grade its own work #AI #SoftwareEngineering #LLM

@dev_community An 8B Agent That Thinks Without Writing Tokens Beats GPT-5.6 Luna on GAIA. Not on HLE #AI #LLM #OpenSource

@lesswrong On Qwen, the J-lens readouts at the newline token reveal lies #AI #Rationality #LLM

@dev_community Tīrtha Bench: the model data coders actually need (and what we're building next) #AI #LLM #DataScience

@simon_willison llm-echo 0.5 #AI #LLM #OpenSource

@dev_community My LLM chat API taught me that '50+ models' is a maintenance tax, not a feature #AI #LLM #Tech

@dev_community Local AI computer use: a model that clicks for you, and the questions it asks first #AI #OpenSource #LLM

@dev_community HybridAgent: Reduza Tokens e Potencialize Seu LLM #AI #LLM #Dev

@dev_community HybridAgent: Cut Token Costs with Latent‑Space Reasoning #AI #LLM #OpenSource

@dev_community Running Qwen Code on a Custom OpenAI-Compatible API: modelProviders, a 41,000-Character First Request and Retries That Keep Going for Minutes #AI #LLM #OpenSource

@hackernews If you don't run your own LLM proxy, how do you know whats going on? #HackerNews #Tech #LLM

@dev_community Day 03/90: Hybrid Search in RAG: Can Combining BM25 and Vector Search Find Better Evidence? #AI #Search #LLM

@dev_community The Bell of Greystone #Gaming #LLM #ShowDev

@dev_community Naive RAG is lying to you. Here are the 7 architectures that actually survive production. #AI #MachineLearning #LLM

@dev_community Comparing Qwen and Gemma on the Low End: Qwen Is Faster Without Drafting, Gemma Has Better Quality #AI #LLM #Performance

@dev_community Building a Search & Fetch Layer for LLM Agents: Caching, Clean Extraction and Cost Control in Python #Python #AI #LLM

@dev_community How to Ask ChatGPT, Claude and Gemini the Same Question at Once (and Compare the Answers) #AI #LLM #Productivity

@dev_community The 5-section prompt framework that finally made my LLM output "ship it" instead of "almost right" #AI #LLM #PromptEngineering

@habr_ru Ouroboros, очередной инструмент для вашего harness #Programming #LLM #Debugging

@dev_community Five concepts to learn before you build with LLMs #AI #LLM #BeginnerDev

@the_new_stack Gemini 4 Argon vs. Claude Opus 5.5: Half the price and about half as accurate #AI #LLM #Tech

@dev_community RAG Context Compression: Headroom Cuts Retrieval Token Costs by 57% Without Accuracy Loss #AI #Python #LLM

@dev_community Build Your Own AI Prompt Library: Save and Reuse Prompts Across ChatGPT, Claude and Gemini #AI #Productivity #LLM

@pypi_recent_updates free-llm-models 1.0.2 #Python #OpenSource #LLM

@dev_community DeepSeek swapped its Flash model overnight. I pulled the new config and did the cache math. #AI #OpenSource #LLM

@habr_ru Синтетическая эмпатия: как RAG, системные промпты и TTS инженерят привязанность к LLM-агентам #AI #LLM #Tech

@dev_community Everything You Need to Know About Agents #AI #Agents #LLM

@dev_community Model Context Protocol (MCP) for Local LLMs: Connect Ollama & vLLM to Workstation Tools #AI #LLM #OpenSource

@dev_community vLLM Temperature 0 Isn't Deterministic: 23 of 200 Answers Changed #LLM #AI #Python

@dev_community Your nightly LLM job pays double -- every big vendor gives 50% off for waiting a day #AI #LLM #CostOptimization

@habr_ru Интерпретируемость LLM доказана? #AI #LLM #MachineLearning

@dev_community Prompt Caching: The 90% Discount You're Missing #AI #LLM #Tech

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