Open-Source AI
Open models — Llama, Mistral, DeepSeek, Qwen and others — are catching up to closed labs and let you run AI on your own hardware, vendor-free. That shifts the balance of power, the safety debate and the economics of the field. Here is everything on open-source AI: open-weight releases, licenses, local deployment and the race against closed models.
Open-Source Agent vs. 1C Napar: Hybrid RAG on DeepSeek Wins in Practice
Habr tested a self-built LangGraph agent with hybrid RAG search against the commercial 1C Napar assistant. On three real developer tasks using deepseek-v4-flash…
I Wrote 61 Tests for My AI Mentor. Then I Found Out You Can't Trust the Tests Either
A developer built 61 tests to check an AI mentor on a coding education platform. But the test bench itself had bugs: it marked cut-off answers as passing and let…
When Small LLMs Beat the Swarm: How Splitting Data Into Sections Gave a Weak Model a 4x Boost
A heating-systems engineer ran an experiment with six weak models (qwen2.5-coder-1.5b, llama-3.2-1b, internvl3-2b, and others), borrowing the structure of a design…
Free Open-Source AutoCAD Alternative for 2D and 3D Appears on GitHub
I Ran Qwen on a $50 FPGA: How a Homemade AI Accelerator Works
Unsloth and Llama 3: How to Teach a Model to Call APIs Reliably via JSON
KDnuggets Shows How to Build a Stateless MCP Server in Python With HTTP Access
LLM Development in 2026: RAG, Agents, and Choosing Models
A senior engineer at Finam shares the practice of LLM development: the main direction is integration through RAG and agents. In 90% of cases, small models are…
Westlake Robotics Unveils WR1: A Humanoid That Folds Clothes on Its Own With a Dexterous Hand
Westlake Robotics has unveiled WR1, a "general-purpose brain" for humanoids. The robot moves between household scenes without stopping and, the company claims, is…
10 Free AI Tools to Replace Paid Data Science Software
Open-source video editor Wunjo Make can now get plugins written via Claude Code, Codex and Cursor
Agentgateway Brings LLM, MCP and A2A Traffic Into a Single Open-Source Proxy
Opper releases Jevman: language models play 100 games of Pac-Man each
DOGS Beats 9 Baseline Methods at Logo Generation Across Two Renderers
DOGS drops prompt rewriting: a GFlowNet samples a logo design graph and penalizes similarity to existing marks. The authors compared it with nine baseline methods.
Kolmogorov-Arnold Networks Match MLP Performance With 40% Fewer Samples
In reinforcement learning, KANs reach the same results as MLPs with 40% fewer samples. Peak relative gain is up to 50%, and reward noise does not erase the…