Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the daily issue
Every new post of the day, in one email. Confirmation required.
Research1 min read
Research shows that as few as one or two tokens per reasoning trajectory can incentivize reasoning ability, matching or surpassing full-token training across various models and tasks.
From arXiv cs.AI
LLMs1 min read
PetQA is a Korean QA benchmark with over 10,000 text and multimodal pairs, assessing veterinary knowledge and clinical reasoning in LLMs and LVLMs across various settings.
From arXiv cs.CL
LLMs1 min read
The study examines internal changes in Audio LLMs when trained on data that requires audio for answer determination, highlighting how acoustic information impacts model representations and predictions.
From arXiv cs.CL
LLMs1 min read
Research shows that pause tokens, when used as a training intervention, enhance reasoning capabilities in large language models without compromising language understanding.
From arXiv cs.CL
LLMs1 min read
Three open-weight LLMs were assessed for demographic misalignment across countries using Wasserstein distance; targeted fine-tuning reduced bias but redistributed it among personas.
From arXiv cs.CL
Research1 min read
Enhanced capabilities in large language models may lead to more correlated behaviors, increasing systemic risk, especially when models share reasoning or misinformation environments.
From arXiv cs.AI
Research1 min read
IPGeoAI uses a Transformer Encoder and LLM-derived semantic features to improve city-level IP geolocation accuracy and coverage, outperforming traditional methods.
From arXiv cs.AI
LLMs1 min read
A new benchmark evaluates whether large language models can interpret social meaning in Chinese online comments, focusing on indirect and playful language. The strongest model achieves 81.42% accuracy.
From arXiv cs.CL
Research1 min read
A systematic review traces the development of AI in recruitment from bilateral retrieval to multi-stage workflows, highlighting evaluation gaps and future directions.
From arXiv cs.AI
LLMs1 min read
A distributional theory explains how large language models incorporate external evidence, revealing that model responses are influenced by prior beliefs and evidence characteristics across multiple domains.
From arXiv cs.CL
LLMs1 min read
The August newsletter includes details on OpenAI's cyberattacks, game integrations with Fable 5 and Sol 5.6, and updates on ChatGPT work models, offering insights for engineers managing models and agents.
From Simon Willison
Models1 min read
Playco utilized GPT-6 Astra to develop three themed game prototypes from a single grey box, achieving a 50% reduction in manual fixes compared to previous models.
From OpenAI news
LLMs1 min read
Alibaba has released the open weights for Qwen3.8-2.4T-A95B, a 2.4 trillion parameter model, allowing near-frontier capabilities to be deployed on NVIDIA GB300 NVL72 systems. This enables engineers to run large language models with configurable reasoning.
From NVIDIA technical blog
Research1 min read
Gemini 3.7 Flash is a new language model introduced by Google DeepMind, designed for improved performance and efficiency in AI applications.
From Google DeepMind blog
Research1 min read
Google DeepMind and A24 have initiated a research partnership focused on developing advanced AI agents. The collaboration aims to explore the use of large language models in creative workflows, specifically for scriptwriting.
From Google DeepMind blog
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
How this blog is made
Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace.
Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run the same pipeline yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.
