A newsletter breaking down AI research, technology, and Australian property in plain English
Google DeepMind is testing a Gemini Flash Lite model against confidential benchmarks sealed in a cryptographic box, with four external partners.
A multi-agent framework from the University of Stuttgart lets LLM agents design, run, and interpret experiments on pharmaceutical simulation models.
TradingAgents, an open-source multi-agent LLM framework modelling a trading desk with arguing AI agents, approaches 100,000 GitHub stars.
LanceDB, an open-source embedded vector database in Rust, hit GitHub's daily trending list with 11,000-plus stars and bold multimodal search claims.
An arXiv preprint found adding security requirements to AI coding prompts cut confirmed flaws from 51 to 24 across six web apps, with zero critical issues.
Google's Gemini CLI offers 1,000 free AI requests daily in the terminal, with a 1M token context window and Gemini 3 models. Now 106,000 stars.
Purdue researchers found stricter EU regulatory formatting makes LLMs hallucinate more, while vaguer rules need heavier prompts for consistent output.
SRPO turns a model's completed reasoning into per-token training signals without external critics and hits 73.3% on AIME'24 with Qwen3-8B at 8% of the
A new distillation recipe shrinks LLM safety guards to run on commodity CPUs in 24ms, matching 8-billion-parameter teachers on adversarial prompts.
