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
arXiv:2609.13559v1 Announce Type: new Abstract: Large Language Models (LLMs) with function-calling capabilities are becoming critical for modern agentic AI systems. Nevertheless, current deployments typically route inferences to powerful...
From arXiv cs.AI
LLMs1 min read
arXiv:2609.13682v1 Announce Type: new Abstract: We introduce LayerRoute, a parameter-efficient method for adaptive transformer layer-skipping that combines per-layer hard-gated routing (trained via a straight-through estimator) with join...
From arXiv cs.CL
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.
AI3 min read
OpenSmartRoute provides a flexible layer for engineers to integrate LLM tools into their workflows. This guide explains how the router utilizes tools,...
From growth-engine
LLMs1 min read
ChatGPT Work, using GPT-6 Astra, created 5K and 10K running routes based on a user’s address, leveraging OpenStreetMap data. The process highlights challenges with LLM transparency and the need for agent tool call preservation.
From Simon Willison on LLMs
AI3 min read
Simplify complex AI workflows with OpenSmartRoute’s multi-model orchestration capabilities. Route requests across multiple LLMs, dynamically adjusting the...
From growth-engine
LLMs1 min read
OpenRouter automatically selects the most cost-effective backend provider for model requests, handling variations in serving software and capabilities. Using the provider.only option allows control over routing for specific model IDs.
From Simon Willison
AI1 min read
Moonshot AI projects $2 billion in annual revenue for its K3 model by the end of the year, doubling its August run rate. This reflects the model’s usage, currently generating 300 billion tokens daily, despite recent declines.
From TechCrunch AI
Agents1 min read
Amazon SageMaker Inference introduced prefix-aware routing, which optimizes LLM latency by directing requests with matching prompt prefixes to the same instance. This results in improved KV cache hit rates and reduced time-to-first-token, particularly for models like Llama 3.1 70B.
From AWS machine learning blog
Research1 min read
A new multi-agent system is introduced for Arctic eco-navigation, integrating operational, physical, ecological, and community criteria within a unified routing framework. The system provides safer, more transparent, and socially responsible route planning for Arctic maritime operations.
From arXiv cs.AI
LLMs1 min read
Research found that combining query rewriting with a strong RAG baseline yields significant improvements in retrieval accuracy, primarily due to the complementary nature of different rewriting strategies. A cost-aware router further optimizes this approach, reducing rewriting costs while maintaining performance.
From arXiv cs.CL
Agents1 min read
A LiteLLM gateway can be deployed on Amazon ECS with AWS Fargate, connecting to OpenAI models on Amazon Bedrock, with request routing via Codex and configurable controls.
From AWS machine learning blog
LLMs1 min read
We ran 900 DeepSWE rollouts on GLM-5.3 and GLM-5.3 Flash. Flash gives up 5.6 points of pass@1 at 17x lower cost, and only 2.6 points at pass@4.
From Together AI blog
LLMs1 min read
We ran 904 DeepSWE rollouts on GLM-5.3 and Claude Fable 5. A tie on pass@1, but GLM-5.3 wins pass@4 and costs 5.4x less: \$3.99 per rollout vs. \$21.63.
From Together AI blog
LLMs1 min read
We ran 904 DeepSWE rollouts on GLM-5.3 and GPT-5.6 Sol. Sol leads pass@1 by 3.7 points; GLM-5.3 wins pass@4 at half the cost, and a GLM-first cascade hits 85.9%.
From Together AI blog
LLMs1 min read
We ran 904 DeepSWE rollouts on DeepSeek V4 Pro 0813 and GPT-5.6 Sol. Sol leads pass@1 by 10 points at 35x the cost; Pro wins pass@4, and a Pro-first cascade hits 83.0%.
From Together AI blog
LLMs1 min read
We ran 904 DeepSWE rollouts on DeepSeek V4 Pro 0813 and Claude Fable 5. Fable leads pass@1 at 90x the cost; Pro wins pass@4, and a Pro-first cascade hits 82.7%.
From Together AI blog
LLMs1 min read
Together AI allows engineers to conduct A/B tests in production by splitting traffic between model variants. This enables real-world measurement of model performance against the control, using a flexible endpoint-level routing system.
From Together AI 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.
