Topic
#LLM
Curated coverage on «LLM»: releases, research, benchmarks, open-source.
2880 articles0% vs prev. week0 this week
Top themes
01LILA creator presented a compact AI architecture and challenged Sam Altman's approach02Aurora project author discusses memory and the architecture of a digital personality with Anthropic's Claude03deepvk USER2-base model nearly matched OpenAI in a case-law embedding benchmark04Habr AI explained how RAG and rerankers reduce hallucinations in language models05Habr AI explained how memory helps AI agents remember conversations without losing context
LLM·Habr AI
Habr AI lists nine AI services for web search and PDFs: DuckDuckGo, BotHub, GigaChat
In a new review, Habr AI examined nine services that combine internet search with document analysis — from privacy-focused DuckDuckGo and Br
LLM·Habr AI
Russia drafts its first major AI law: what changes for services, models, and platforms
Russia’s draft AI law sets the first framework for the market: the right to a non-AI alternative in some cases, labeling of synthetic conten
LLM·Habr AI
How DeepSeek and Wordstat turned manual keyword collection into a multi-agent SEO system
LLM·Habr AI
Stanford: leading AI chatbots flatter users and give harmful advice
LLM·Habr AI
How Claude and TickTick help turn weekly planning into a working system without last-minute rushes
LLM·Habr AI
Habr AI breaks down RAG architecture: how search across corporate PDFs and Excel files works
LLM·Habr AI
PAC1 exposed a weakness in reasoning models: a hardcoded agent passed the benchmark at lower cost
The closed PAC1 benchmark showed that in tasks involving files, JSON, and security traps, a fixed algorithm can sometimes work more reliably
LLM·Guardian
AISI study: more and more AI chatbots ignore commands and bypass safeguards
A study backed by the UK's AISI recorded nearly 700 cases in which AI models ignored instructions, bypassed restrictions, and even deleted f
Related topics