Topic
#LLM
Curated coverage on «LLM»: releases, research, benchmarks, open-source.
2850 articles-58% vs prev. week57 this week
Top themes
01YuMoney Built RAG Platform and AI Assistant Eugene for Corporate Wiki Search02Claude Sonnet 5 vs Opus 4.8: agentic coding comparison and API pricing from Anthropic03Did GitHub become more uniform after ChatGPT? Code study for 2019–202504LLM agents and SOC: developers built a cyber threat database using RAG05Kimi K2.7 Code versus Claude Fable 5: landing pages 94% cheaper
LLM·arXiv cs.LG
ROAM Framework Adapts Industrial AI Models to New Scenarios Without Retraining
Researchers presented ROAM — a method that uses LLM reasoning to adapt already-trained industrial models to new conditions without retrainin
LLM·arXiv cs.LG
Scientists Propose TSF Method: LLM Improves Industrial Process Forecasting
New Task-Semantic Field Factorization method uses language models to annotate industrial data and reduces forecast error by 6.4% on average.
LLM·arXiv cs.CL
Multilingual Transcripts and Distillation Help AI Better Detect Emotion in Speech
LLM·arXiv cs.AI
Agents on GPT-4o-mini and GPT-5.2 Silently Break Rules in τ²-bench Tests
LLM·3DNews AI
Apple Negotiates with PrismML to Compress AI Models Like Qwen 3.6 for iPhone
LLM·TNW
Gartner: Customers Choose ChatGPT Three Times More Often Than Company Chatbots
LLM·Habr AI
CyberOK Tested Phone Scammer Tactics on Claude, GPT-5.5, Qwen, and DeepSeek
Researcher Sergey Gordeychik from CyberOK Research applied classic phone scammer influence techniques to seven language models, including Cl
LLM·Habr AI
Spec-Driven Development: How AI Changes the Role of System Analyst in 2026
A system analyst with six years of experience explains on Habr how the Spec-Driven Development approach changes the work of analysts impleme
Related topics